QuickSearch:
  Number of matching entries: 0.

You can search over all the following column properties (e.g year, author, title)
Last Update on 16/04/2015
AuthorTitleYearJournal/ProceedingsBibTeX typeDOI/URL/PDF
Buhmann, J. M., Gronskiy, A. & Szpankowski, W. Free Energy Rates for a Class of Very Noisy Optimization Problems 2014 Proceedings of the 25th International Conference on Probabilistic, Combinatorial and Asymptotic Methods for the Analysis of Algorithms   inproceedings  
BibTeX:
@inproceedings{Bhmnn2014,
  author = {Buhmann, Joachim M. and Gronskiy, Alexey and Szpankowski, Wojciech},
  title = {{F}ree {E}nergy {R}ates for a {C}lass of {V}ery {N}oisy {O}ptimization {P}roblems},
  booktitle = {Proceedings of the 25th International Conference on Probabilistic, Combinatorial and Asymptotic Methods for the Analysis of Algorithms},
  publisher = {LORIA},
  year = {2014},
  volume = {BA},
  pages = {61--72}
}
Balduzzi, D. Cortical prediction markets 2014   inproceedings  
BibTeX:
@inproceedings{Bldzz2014,
  author = {Balduzzi, David},
  title = {{C}ortical prediction markets},
  publisher = {FAAMAS},
  year = {2014},
  volume = {13},
  pages = {1265--1272}
}
Brodersen, K. H., Deserno, L., Schlagenhauf, F., Lin, Z., Penny, W. D., Buhmann, J. M. & Stephan, K. E. Dissecting psychiatric spectrum disorders by generative embedding 2014 Neuroimage Clinical   article  
BibTeX:
@article{Brdrsn2014,
  author = {Brodersen, Kay H. and Deserno, Lorenz and Schlagenhauf, Florian and Lin, Zhihao and Penny, Will D. and Buhmann, Joachim M. and Stephan, Klaas E.},
  title = {{D}issecting psychiatric spectrum disorders by generative embedding},
  journal = {Neuroimage Clinical},
  year = {2014},
  volume = {4},
  pages = {98--111}
}
D. Mahapatra, P. Schueffler, J. T. C. P. J. M. A. M. R. A. J. S. S. T. F. V. J. B. Combining Multiple Expert Annotations Using Semi-Supervised Learning And Graph Cuts For Crohntextquoterights Disease Segmentation 2014   inproceedings  
BibTeX:
@inproceedings{D2014,
  author = {D. Mahapatra, P. Schueffler, J. Tielbeek, C. Puylaert, J. Makanyanga, A. Menys, R. Andriantsimiavona, J. Stoker, S. Taylor, F.M. Vos, J.M. Buhmann},
  title = {{C}ombining {M}ultiple {E}xpert {A}nnotations {U}sing {S}emi-{S}upervised {L}earning {A}nd {G}raph {C}uts {F}or {C}rohn{\textquoteright}s {D}isease {S}egmentation},
  year = {2014}
}
Floros, X. Exploiting model structure for efficient hybrid dynamical systems simulation 2014   phdthesis  
BibTeX:
@phdthesis{Floros2014,
  author = {Floros, Xenofon},
  title = {{E}xploiting model structure for efficient hybrid dynamical systems simulation},
  year = {2014}
}
Floros, X., Bergero, F., Ceriani, N., Casella, F., Kofmann, E. & Cellier, F. E. Simulation of Smart-Grid Models using Quantization-Based Integration Methods 2014   inproceedings  
BibTeX:
@inproceedings{Flrs2014,
  author = {Floros, Xenofon and Bergero, Federico and Ceriani, Nicola and Casella, Francesco and Kofmann, Ernesto and Cellier, Fran{\c{c}}ois E.},
  title = {{S}imulation of {S}mart-{G}rid {M}odels using {Q}uantization-{B}ased {I}ntegration {M}ethods},
  year = {2014}
}
Gomez-Rodriguez, M., Leskovec, J., Balduzzi, D. & Schölkopf, B. Uncovering the Structure and Temporal Dynamics of Information Propagation 2014 Network science   article  
BibTeX:
@article{Gmz2014,
  author = {Gomez-Rodriguez, Manuel and Leskovec, Jure and Balduzzi, David and Sch{\"{o}}lkopf, Bernhard},
  title = {{U}ncovering the {S}tructure and {T}emporal {D}ynamics of {I}nformation {P}ropagation},
  journal = {Network science},
  year = {2014},
  volume = {2},
  number = {1},
  pages = {26--65}
}
Gronskiy, A. & Buhmann, J. M. How informative are Minimum Spanning Tree algorithms? 2014 2014 IEEE International Symposium on Information Theory (ISIT)   inproceedings  
BibTeX:
@inproceedings{Grnsky2014,
  author = {Gronskiy, Alexey and Buhmann, Joachim M.},
  title = {{H}ow informative are {M}inimum {S}panning {T}ree algorithms?},
  booktitle = {2014 IEEE International Symposium on Information Theory (ISIT)},
  publisher = {IEEE},
  year = {2014},
  pages = {2277--2281}
}
Giesen, C., Wang, H. A., Schapiro, D., Zivanovic, N., Jacobs, A., Hattendorf, B., Schüffler, P. J., Grolimund, D., Buhmann, J. M., Brandt, S., Varga, Z., Wild, P. J., Günther, D. & Bodenmiller, B. Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometry 2014 Nature Methods   article  
BibTeX:
@article{Gsn2014,
  author = {Giesen, Charlotte and Wang, Hao A.O. and Schapiro, Denis and Zivanovic, Nevena and Jacobs, Andrea and Hattendorf, Bodo and Sch{\"{u}}ffler, Peter J. and Grolimund, Daniel and Buhmann, Joachim M. and Brandt, Simone and Varga, Zsuzsanna and Wild, Peter J. and G{\"{u}}nther, Detlef and Bodenmiller, Bernd},
  title = {{H}ighly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometry},
  journal = {Nature Methods},
  year = {2014},
  volume = {11},
  number = {4},
  pages = {417--422}
}
Laptev, D. & Buhmann, J. M. Convolutional Decision Trees for Feature Learning and Segmentation 2014 Pattern Recognition : 36th German Conference, GCPR 2014, Münster, Germany, September 2-5, 2014, Proceedings   inproceedings  
BibTeX:
@inproceedings{Laptev2014,
  author = {Laptev, Dmitry and Buhmann, Joachim M.},
  title = {{C}onvolutional {D}ecision {T}rees for {F}eature {L}earning and {S}egmentation},
  booktitle = {Pattern Recognition : 36th German Conference, GCPR 2014, M{\"{u}}nster, Germany, September 2-5, 2014, Proceedings},
  publisher = {Springer International Publishing},
  year = {2014},
  volume = {8753},
  pages = {95--106}
}
Laptev, D. & Buhmann, J. M. SuperSlicing Frame Restoration for Anisotropic ssTEM and Video Data 2014 Challenges in Machine Learning Volume 11: Connectomics (ECML 2014)   inproceedings  
BibTeX:
@inproceedings{Laptev2014a,
  author = {Laptev, Dmitry and Buhmann, Joachim M.},
  title = {{S}uper{S}licing {F}rame {R}estoration for {A}nisotropic ss{T}{E}{M} and {V}ideo {D}ata},
  booktitle = {Challenges in Machine Learning Volume 11: Connectomics (ECML 2014)},
  publisher = {JMLR},
  year = {2014}
}
Laptev, D., Tikhonov, A., Serdyukov, P. & Gusev, G. Parameter-Free Discovery and Recommendation of Areas-of-Interest 2014 Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems   inproceedings  
BibTeX:
@inproceedings{Laptev2014b,
  author = {Laptev, Dmitry and Tikhonov, Alexey and Serdyukov, Pavel and Gusev, Gleb},
  title = {{P}arameter-{F}ree {D}iscovery and {R}ecommendation of {A}reas-of-{I}nterest},
  booktitle = {Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},
  publisher = {ACM},
  year = {2014},
  pages = {113--122}
}
Laptev, D., Vezhnevets, A. & Buhman, J. M. SuperSlicing Frame Restoration for Anisotropic ssTEM 2014   inproceedings  
BibTeX:
@inproceedings{Lptv2014,
  author = {Laptev, Dmitry and Vezhnevets, Alexander and Buhman, Joachim M.},
  title = {{S}uper{S}licing {F}rame {R}estoration for {A}nisotropic ss{T}{E}{M}},
  year = {2014},
  pages = {1198--1201}
}
Mahapatra, D. & Buhmann, J. M. Prostate MRI Segmentation Using Learned Semantic Knowledge and Graph Cuts 2014 IEEE transactions on biomedical engineering   article  
BibTeX:
@article{Mahapatra2014,
  author = {Mahapatra, Dwarikanath and Buhmann, Joachim M.},
  title = {{P}rostate {M}{R}{I} {S}egmentation {U}sing {L}earned {S}emantic {K}nowledge and {G}raph {C}uts},
  journal = {IEEE transactions on biomedical engineering},
  year = {2014},
  volume = {61},
  number = {3},
  pages = {756--764}
}
McWilliams, B., Krummenacher, G., Lucic, M. & Buhmann, J. M. Fast and Robust Least Squares Estimation in Corrupted Linear Models 2014   inproceedings  
BibTeX:
@inproceedings{McWllms2014,
  author = {McWilliams, Brian and Krummenacher, Gabriel and Lucic, Mario and Buhmann, Joachim M.},
  title = {{F}ast and {R}obust {L}east {S}quares {E}stimation in {C}orrupted {L}inear {M}odels},
  publisher = {MIT Press, 1989-},
  year = {2014},
  volume = {27}
}
Mahapatra, D., Schüffler, P. J., Tielbeek, J. A. W., Makanyanga, J. C., Stoker, J., Taylor, S. A., Vos, F. M. & Buhmann, J. M. Active learning based segmentation of Crohn's disease using principles of visual saliency 2014 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)   inproceedings  
BibTeX:
@inproceedings{Mhptr2014,
  author = {Mahapatra, Dwarikanath and Sch{\"{u}}ffler, Peter J. and Tielbeek, Jeroen A. W. and Makanyanga, Jesica C. and Stoker, Jaap and Taylor, Stuart A. and Vos, Franciscus M. and Buhmann, Joachim M.},
  title = {{A}ctive learning based segmentation of {C}rohn's disease using principles of visual saliency},
  booktitle = {2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)},
  publisher = {IEEE},
  year = {2014},
  pages = {226--229}
}
Mathys, C. D., Lomakina, E. L., Daunizeau, J., Iglesias, S., Brodersen, K. H., Friston, K. J. & Stephan, K. E. Uncertainty in perception and the Hierarchical Gaussian Filter 2014 Frontiers in Human Neuroscience   article  
BibTeX:
@article{Mthys2014,
  author = {Mathys, Christoph D. and Lomakina, Ekaterina L. and Daunizeau, Jean and Iglesias, Sandra and Brodersen, Kay H. and Friston, Karl J. and Stephan, Klaas E.},
  title = {{U}ncertainty in perception and the {H}ierarchical {G}aussian {F}ilter},
  journal = {Frontiers in Human Neuroscience},
  year = {2014},
  volume = {8},
  pages = {825--}
}
P.J. Schüffler, D. Mahapatra, J. T. F. V. J. M. D. P. C. N. J. S. S. T. J. B. Semi Automatic Crohntextquoterights Disease Severity Assessment on MR Imaging 2014   inproceedings  
BibTeX:
@inproceedings{PJ2014,
  author = {P.J. Sch{\"{u}}ffler, D. Mahapatra,J.A.W. Tielbeek,F.M. Vos,J. Makanyanga,D.A. Pends{\'{e}},C.Y. Nio,J. Stoker,S.A. Taylor,J.M. Buhmann},
  title = {{S}emi {A}utomatic {C}rohn{\textquoteright}s {D}isease {S}everity {A}ssessment on {M}{R} {I}maging},
  year = {2014}
}
Rechsteiner, M. P., Floros, X., Boehm, B. O., Marselli, L., Marchetti, P., Stoffel, M., Moch, H. & Spinas, G. A. Automated Assessment of Beta-Cell Area and Density per Islet and Patient Using TMEM27 and BACE2 Immunofluorescence Staining in Human Pancreatic Beta-Cells 2014 PLoS ONE   article  
BibTeX:
@article{Rchstnr2014,
  author = {Rechsteiner, Markus P. and Floros, Xenofon and Boehm, Bernhard O. and Marselli, Lorella and Marchetti, Piero and Stoffel, Markus and Moch, Holger and Spinas, Giatgen A.},
  title = {{A}utomated {A}ssessment of Beta-{C}ell {A}rea and {D}ensity per {I}slet and {P}atient {U}sing {T}{M}{E}{M}27 and {B}{A}{C}{E}2 {I}mmunofluorescence {S}taining in {H}uman {P}ancreatic Beta-{C}ells},
  journal = {PLoS ONE},
  year = {2014},
  volume = {9},
  number = {6},
  pages = {e98932--}
}
Schüffler, P. J., Schapiro, D., Giesen, C., Wang, H., Bodenmiller, B. & Buhmann, J. M. Single Cell Segmentation with Watersheds on Highly Multiplexed Images 2014 Proceedings of the 12th European Congress on Digital Pathology   inproceedings  
BibTeX:
@inproceedings{Schfflr2014,
  author = {Sch{\"{u}}ffler, Peter J. and Schapiro, D. and Giesen, C. and Wang, H.A.O. and Bodenmiller, B. and Buhmann, Joachim M.},
  title = {{S}ingle {C}ell {S}egmentation with {W}atersheds on {H}ighly {M}ultiplexed {I}mages},
  booktitle = {Proceedings of the 12th European Congress on Digital Pathology},
  publisher = {12th European Congress on Digital Pathology},
  year = {2014}
}
Schüffler, P. J. Machine learning approaches for structure analysis in medical image data 2014   phdthesis  
BibTeX:
@phdthesis{Schuffler2014,
  author = {Sch{\"{u}}ffler, Peter J.},
  title = {{M}achine learning approaches for structure analysis in medical image data},
  year = {2014}
}
Schüffler, P. J., Mahapatra, D., Vos, F. M. & Buhmann, J. M. Computer Aided Crohn's Disease Severity Assessment in MRI 2014   inproceedings  
BibTeX:
@inproceedings{Schuffler2014a,
  author = {Sch{\"{u}}ffler, Peter J. and Mahapatra, Dwarikanath and Vos, Franciscus M. and Buhmann, Joachim M.},
  title = {{C}omputer {A}ided {C}rohn's {D}isease {S}everity {A}ssessment in {M}{R}{I}},
  publisher = {VIGOR++ Workshop 2014 - Showcase of Research Outcomes and Future Outlook},
  year = {2014}
}
Streich, A. & Buhmann, J. Asymptotic analysis of estimators on multi-label data 2014 Machine learning   article  
BibTeX:
@article{Strch2014,
  author = {Streich, A.P. and Buhmann, J.M.},
  title = {{A}symptotic analysis of estimators on multi-label data},
  journal = {Machine learning},
  year = {2014}
}
Wulff, S. Convex optimization as a building block for difficult problems in machine learning 2014   phdthesis  
BibTeX:
@phdthesis{Wlff2014,
  author = {Wulff, Sharon},
  title = {{C}onvex optimization as a building block for difficult problems in machine learning},
  year = {2014}
}
Zhou, G., Geman, S. & Buhmann, J. M. Sparse feature selection by information theory 2014 2014 IEEE International Symposium on Information Theory   inproceedings  
BibTeX:
@inproceedings{Zh2014,
  author = {Zhou, Guangyao and Geman, Stuart and Buhmann, Joachim M.},
  title = {{S}parse feature selection by information theory},
  booktitle = {2014 IEEE International Symposium on Information Theory},
  publisher = {IEEE},
  year = {2014},
  pages = {926--930}
}
Janzing, D., Balduzzi, D., Grosse-Wentrup, M. & Schölkopf, B. Quantifying causal influences 2013 Annals of Statistics   article  
BibTeX:
@article{jbgs:13,
  author = {D Janzing and D Balduzzi and Moritz Grosse-Wentrup and Bernhard Sch{\"o}lkopf},
  title = {Quantifying causal influences},
  journal = {Annals of Statistics},
  year = {2013},
  volume = {41},
  number = {5},
  pages = {2324-2358}
}
Buhmann, Joachim M.. SIMBAD: Emergence of Pattern Similarity 2013 Similarity-Based Pattern Analysis and Recognition   incollection DOI URL  
BibTeX:
@incollection{JMB:SIMBAD-book:2013,
  author = {{Joachim M.} Buhmann},
  title = {SIMBAD: Emergence of Pattern Similarity},
  booktitle = {Similarity-Based Pattern Analysis and Recognition},
  publisher = {Springer Berlin / Heidelberg},
  year = {2013},
  pages = {45-64},
  url = {http://dx.doi.org/10.1007/978-1-4471-5628-4_3},
  doi = {10.1007/978-1-4471-5628-4_3}
}
McWilliams, B., Balduzzi, D. & Buhmann, J. Correlated random features for fast semi-supervised learning 2013 Adv in Neural Information Processing Systems (NIPS)   inproceedings  
BibTeX:
@inproceedings{mbb:13,
  author = {Brian McWilliams and David Balduzzi and Joachim Buhmann},
  title = {Correlated random features for fast semi-supervised learning},
  booktitle = {Adv in Neural Information Processing Systems (NIPS)},
  year = {2013}
}
Muandet, K., Balduzzi, D. & Schölkopf, B. Domain Generalization via Invariant Feature Representation 2013 30th International Conference on Machine Learning (ICML)   incollection  
Abstract: This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based optimization algorithm that learns an invariant transformation by minimizing the dissimilarity across domains, whilst preserving the functional relationship between input and output variables. A learning-theoretic analysis shows that reducing dissimilarity improves the expected generalization ability of classifiers on new domains, motivating the proposed algorithm. Experimental results on synthetic and real-world datasets demonstrate that DICA successfully learns invariant features and improves classifier performance in practice.
BibTeX:
@incollection{muandet2013,
  author = {Krikamol Muandet and David Balduzzi and Bernhard Sch{\"o}lkopf},
  title = {Domain Generalization via Invariant Feature Representation},
  booktitle = {30th International Conference on Machine Learning (ICML)},
  year = {2013}
}
Schüffler, P., Mahapatra, D., Tielbeek, J. A., Vos, F. M., Makanyanga, J., Pendsé, D., Nio, C., Stoker, J., Taylor, S. & Buhmann, J. M. A Model Development Pipeline for Crohn’s Disease Severity Assessment from Magnetic Resonance Images 2013 Abdominal Imaging. Computation and Clinical Applications   incollection DOI URL  
BibTeX:
@incollection{raey,
  author = {Sch\"uffler, PeterJ. and Mahapatra, Dwarikanath and Tielbeek, Jeroen A.W. and Vos, Franciscus M. and Makanyanga, Jesica and Pends\'e, DougA. and Nio, C.Yung and Stoker, Jaap and Taylor, StuartA. and Buhmann, Joachim M.},
  title = {A Model Development Pipeline for Crohn’s Disease Severity Assessment from Magnetic Resonance Images},
  booktitle = {Abdominal Imaging. Computation and Clinical Applications},
  publisher = {Springer Berlin Heidelberg},
  year = {2013},
  volume = {8198},
  pages = {1-10},
  url = {http://dx.doi.org/10.1007/978-3-642-41083-3_1},
  doi = {10.1007/978-3-642-41083-3_1}
}
Schüffler, P. J., Fuchs, T. J., Ong, C. S., Wild, P. J., J, R. N. & Buhmann, J. M. TMARKER: A free software toolkit for histopathological cell counting and staining estimation 2013 Journal of Pathology Informatics   article DOI URL  
Abstract: Background: Histological tissue analysis often involves manual cell counting and staining estimation of cancerous cells. These assessments are extremely time consuming, highly subjective and prone to error, since immunohistochemically stained cancer tissues usually show high variability in cell sizes, morphological structures and staining quality. To facilitate reproducible analysis in clinical practice as well as for cancer research, objective computer assisted staining estimation is highly desirable. Methods: We employ machine learning algorithms as randomized decision trees and support vector machines for nucleus detection and classification. Superpixels as segmentation over the tissue image are classified into foreground and background and thereafter into malignant and benign, learning from the user's feedback. As a fast alternative without nucleus classification, the existing color deconvolution method is incorporated. Results: Our program TMARKER connects already available workflows for computational pathology and immunohistochemical tissue rating with modern active learning algorithms from machine learning and computer vision. On a test dataset of human renal clear cell carcinoma and prostate carcinoma, the performance of the used algorithms is equivalent to two independent pathologists for nucleus detection and classification. Conclusion: We present a novel, free and operating system independent software package for computational cell counting and staining estimation, supporting IHC stained tissue analysis in clinic and for research. Proprietary toolboxes for similar tasks are expensive, bound to specific commercial hardware (e.g. a microscope) and mostly not quantitatively validated in terms of performance and reproducibility. We are confident that the presented software package will proof valuable for the scientific community and we anticipate a broader application domain due to the possibility to interactively learn models for new image types.
BibTeX:
@article{Schueffler2013,
  author = {Sch\"uffler, Peter J and Fuchs, Thomas J and Ong, Cheng Soon and Wild, Peter J and Rupp Niels J and Buhmann, Joachim M},
  title = {{TMARKER: A free software toolkit for histopathological cell counting and staining estimation}},
  journal = {Journal of Pathology Informatics},
  year = {2013},
  volume = {4},
  number = {2},
  pages = {2},
  url = {http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2013;volume=4;issue=2;spage=2;epage=2;aulast=Sch%FCffler;t=6},
  doi = {10.4103/2153-3539.109804}
}
Sigg, C., Dikk, T. & Buhmann, J. Speech Enhancement Using Generative Dictionary Learning 2012 Audio, Speech, and Language Processing, IEEE Transactions on   article DOI  
BibTeX:
@article{6146452,
  author = {Sigg, C.D. and Dikk, T. and Buhmann, J.M.},
  title = {Speech Enhancement Using Generative Dictionary Learning},
  journal = {Audio, Speech, and Language Processing, IEEE Transactions on},
  year = {2012},
  volume = {20},
  number = {6},
  pages = {1698 -1712},
  doi = {10.1109/TASL.2012.2187194}
}
Sigg, C., Dikk, T. & Buhmann, J. Learning Dictionaries With Bounded Self-Coherence 2012 Signal Processing Letters, IEEE   article DOI  
BibTeX:
@article{6328247,
  author = {Sigg, C.D. and Dikk, T. and Buhmann, J.M.},
  title = {Learning Dictionaries With Bounded Self-Coherence},
  journal = {Signal Processing Letters, IEEE},
  year = {2012},
  volume = {19},
  number = {12},
  pages = {861 -864},
  doi = {10.1109/LSP.2012.2223757}
}
Balduzzi, D. & Besserve, M. Towards a learning-theoretic analysis of spike-timing dependent plasticity 2012 Advances in Neural Information Processing Systems (NIPS) 25   incollection URL  
Abstract: This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to theoretical analysis. We show that the selectron encodes reward estimates into spikes and that an error bound on spikes is controlled by a spiking margin and the sum of synaptic weights. Moreover, the efficacy of spikes (their usefulness to other reward maximizing selectrons) also depends on total synaptic strength. Finally, based on our analysis, we propose a regularized version of STDP, and show the regularization improves the robustness of neuronal learning when faced with multiple stimuli.
BibTeX:
@incollection{balduzzi2012,
  author = {David Balduzzi and Michel Besserve},
  title = {Towards a learning-theoretic analysis of spike-timing dependent plasticity},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 25},
  year = {2012},
  pages = {2465--2473},
  url = {http://books.nips.cc/papers/files/nips25/NIPS2012_1182.pdf}
}
Balduzzi, D. Regulating the information in spikes: a useful bias 2012 NIPS Workshop on Information in Perception and Action   inproceedings  
BibTeX:
@inproceedings{balduzzi2012a,
  author = {David Balduzzi},
  title = {Regulating the information in spikes: a useful bias},
  booktitle = {NIPS Workshop on Information in Perception and Action},
  year = {2012}
}
Brodersen, K. H., Wiech, K., Lomakina, E. I., Lin, C.-s., Buhmann, J. M., Bingel, U., Ploner, M., Stephan, K. E. & Tracey, I. Decoding the perception of pain from fMRI using multivariate pattern analysis 2012 NeuroImage   article DOI URL  
Abstract: Pain is known to comprise sensory, cognitive, and affective aspects. Despite numerous previous fMRI studies, however, it remains open which spatial distribution of activity is sufficient to encode whether a stimulus is perceived as painful or not. In this study, we analysed fMRI data from a perceptual decision-making task in which participants were exposed to near-threshold laser pulses. Using multivariate analyses on different spatial scales, we investigated the predictive capacity of fMRI data for decoding whether a stimulus had been perceived as painful. Our analysis yielded a rank order of brain regions: during pain anticipation, activity in the periaqueductal grey (PAG) and orbitofrontal cortex (OFC) afforded the most accurate trial-by-trial discrimination between painful and non-painful experiences; whereas during the actual stimulation, primary and secondary somatosensory cortex, anterior insula, dorsolateral and ventrolateral prefrontal cortex, and OFC were most discriminative. The most accurate prediction of pain perception from the stimulation period, however, was enabled by the combined activity in pain regions commonly referred to as the ‘pain matrix’. Our results demonstrate that the neural representation of (near-threshold) pain is spatially distributed and can be best described at an intermediate spatial scale. In addition to its utility in establishing structure-function mappings, our approach affords trial-by-trial predictions and thus represents a step towards the goal of establishing an objective neuronal marker of pain perception.
BibTeX:
@article{brodersen_decoding_2012,
  author = {Brodersen, Kay H. and Wiech, Katja and Lomakina, Ekaterina I. and Lin, Chia-shu and Buhmann, Joachim M. and Bingel, Ulrike and Ploner, Markus and Stephan, Klaas Enno and Tracey, Irene},
  title = {Decoding the perception of pain from {fMRI} using multivariate pattern analysis},
  journal = {{NeuroImage}},
  year = {2012},
  url = {http://www.sciencedirect.com/science/article/pii/S105381191200835X?v=s5},
  doi = {10.1016/j.neuroimage.2012.08.035}
}
Brodersen, K. H., Mathys, C., Chumbley, J. R., Daunizeau, J., Ong, C.S.., Buhmann, J. M. & Stephan, K. E. Mixed-effects inference on classification performance in hierarchical datasets 2012 Journal of Machine Learning Research   article  
BibTeX:
@article{brodersen_mixed-effects_2012,
  author = {Brodersen, Kay H. and Mathys, Christoph and Chumbley, Justin R. and Daunizeau, Jean and Ong, {C.S.} and Buhmann, Joachim M. and Stephan, Klaas E.},
  title = {Mixed-effects inference on classification performance in hierarchical datasets},
  journal = {Journal of Machine Learning Research},
  year = {2012}
}
Chehreghani, M. H., Busetto, A. G. & Buhmann, J. M. Information Theoretic Model Validation for Spectral Clustering 2012 Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS) -Journal of Machine Learning Research   article  
BibTeX:
@article{DBLP:journals/jmlr/ChehreghaniBB12,
  author = {Morteza Haghir Chehreghani and Alberto Giovanni Busetto and Joachim M. Buhmann},
  title = {Information Theoretic Model Validation for Spectral Clustering},
  journal = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS) -Journal of Machine Learning Research},
  year = {2012},
  volume = {22},
  pages = {495-503}
}
Laptev, D., Vezhnevets, A., Dwivedi, S. & Buhmann, J. M. Anisotropic ssTEM Image Segmentation Using Dense Correspondence across Sections 2012 MICCAI   inproceedings  
BibTeX:
@inproceedings{DL:AV:SD:JB:MICCAI:2012,
  author = {Dmitry Laptev and Alexander Vezhnevets and Sarvesh Dwivedi and Joachim M. Buhmann},
  title = {Anisotropic ssTEM Image Segmentation Using Dense Correspondence across Sections},
  booktitle = {MICCAI},
  year = {2012},
  pages = {323-330}
}
Bergero, F., Floros, X., Fernández, J., Kofman, E. & Cellier, F. E. Simulating Modelica models with a Stand--Alone Quantized State Systems Solver 2012 9th International Modelica Conference 2012, Munich, Germany   inproceedings DOI URL  
Abstract: This article describes an extension of the OpenModelica Compiler that translates regular Modelica models into a simpler language, called Micro--Modelica ($--Modelica), that can be understood by the recently developed stand--alone Quantized State Systems (QSS) solvers. These solvers are very efficient when simulating systems with frequent discontinuities. Thus, strongly discontinuous Modelica models can be simulated noticeably faster than with the standard discrete time solvers. The simulation of two discontinuous models is analyzed in order to demonstrate the correctness of the proposed implementation as well as the advantages of using the QSS stand-alone solvers.
BibTeX:
@inproceedings{floros_2012,
  author = {Federico Bergero and Xenofon Floros and Joaqu\'{i}n Fern\'{a}ndez and Ernesto Kofman and Fran\c{c}ois E. Cellier},
  title = {{Simulating Modelica models with a Stand--Alone Quantized State Systems Solver}},
  booktitle = {9th International Modelica Conference 2012, Munich, Germany},
  publisher = {Linköping University Electronic Press, Linköpings universitet},
  year = {2012},
  pages = {237-246},
  url = {https://modelica.org/events/modelica2012/Proceedings},
  doi = {10.3384/ecp12076237}
}
Jaggi, M., Lacoste-Julien, S., Schmidt, M. & Pletscher, P. Block-Coordinate Frank-Wolfe for Structural SVMs 2012 NIPS Workshop on Optimization for Machine Learning   inproceedings URL  
BibTeX:
@inproceedings{Jaggi2012,
  author = {Jaggi, Martin and Lacoste-Julien, Simon and Schmidt, Mark and Pletscher, Patrick},
  title = {Block-Coordinate Frank-Wolfe for Structural SVMs},
  booktitle = {NIPS Workshop on Optimization for Machine Learning},
  year = {2012},
  url = {https://ml2.inf.ethz.ch/papers/2012/jaggi2012fwstruct.pdf}
}
Mahapatra, D., Schüffler, P., Tielbeek, J., Buhmann, J. M. & Vos, F. M. A Supervised Learning Based Approach To Detect Crohn's Disease in Abdominal MR Volumes 2012 Proceedings of the MICCAI Workshop on Computational and Clinical Applications in Abdominal Imaging, MICCAI-CCAAI, 2012   inproceedings  
Abstract: We propose a randomized block-coordinate variant of the classic Frank-Wolfe
algorithm for convex optimization with block-separable constraints. Despite its
lower iteration cost, we show that it achieves the same convergence rate as the
full Frank-Wolfe algorithm. We also show that, when applied to the dual struc-
tural support vector machine (SVM) objective, this algorithm has the same low
iteration complexity as primal stochastic subgradient methods. However, unlike
stochastic subgradient methods, the stochastic Frank-Wolfe algorithm allows us to
compute the optimal step-size and yields a computable duality gap guarantee. Our
experiments indicate that this simple algorithm outperforms competing structural
SVM solvers.
BibTeX:
@inproceedings{MahapatraABD2012,
  author = {Dwarikanath Mahapatra and Peter Sch\"uffler and Jeroen Tielbeek and Joachim M. Buhmann and Franciscus M. Vos},
  title = {A Supervised Learning Based Approach To Detect Crohn's Disease in Abdominal MR Volumes },
  booktitle = {Proceedings of the MICCAI Workshop on Computational and Clinical Applications in Abdominal Imaging, MICCAI-CCAAI, 2012},
  publisher = {Springer},
  year = {2012}
}
Ortega, P., Grau-Moya, J., Genewein, T., Balduzzi, D. & Braun, D. A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function 2012 Advances in Neural Information Processing Systems (NIPS) 25   incollection URL  
Abstract: We propose a novel Bayesian approach to solve stochastic optimization problems that involve fnding extrema of noisy, nonlinear functions. Previous work has focused on representing possible functions explicitly, which leads to a two-step procedure of first, doing inference over the function space and second, finding the extrema of these functions. Here we skip the representation step and directly model the distribution over extrema. To this end, we devise a non-parametric conjugate prior based on a kernel regressor. The resulting posterior distribution directly captures the uncertainty over the maximum of the unknown function. We illustrate the effectiveness of our model by optimizing a noisy, high-dimensional, non-convex objective function.
BibTeX:
@incollection{ortega2012,
  author = {Pedro Ortega and Jordi Grau-Moya and Tim Genewein and David Balduzzi and Daniel Braun},
  title = {A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 25},
  year = {2012},
  pages = {3014--3022},
  url = {http://books.nips.cc/papers/files/nips25/NIPS2012_1362.pdf}
}
Pletscher, P. & Kohli, P. Learning low-order models for enforcing high-order statistics 2012 Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS) 2012   inproceedings URL  
BibTeX:
@inproceedings{Pletscher2012a,
  author = {Pletscher, Patrick and Kohli, Pushmeet},
  title = {Learning low-order models for enforcing high-order statistics},
  booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics ({AISTATS}) 2012},
  publisher = {JMLR: W\&CP 22},
  year = {2012},
  pages = {886--894},
  url = {https://ml2.inf.ethz.ch/papers/2012/pletscher2012hol.pdf}
}
Pletscher, P. & Ong, C. S. Part & Clamp: An efficient algorithm for structured output learning 2012 Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS) 2012   inproceedings URL  
BibTeX:
@inproceedings{Pletscher2012b,
  author = {Pletscher, Patrick and Ong, Cheng Soon},
  title = {Part \& Clamp: An efficient algorithm for structured output learning},
  booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics ({AISTATS}) 2012},
  publisher = {JMLR: W\&CP 22},
  year = {2012},
  pages = {877--885},
  url = {https://ml2.inf.ethz.ch/papers/2012/pletscher2012partclamp.pdf}
}
Pletscher, P. & Wulff, S. LPQP for MAP: Putting LP Solvers to Better Use 2012 ICML   inproceedings URL  
BibTeX:
@inproceedings{Pletscher2012c,
  author = {Pletscher, Patrick and Wulff, Sharon},
  title = {{LPQP} for {MAP}: Putting {LP} Solvers to Better Use},
  booktitle = {ICML},
  year = {2012},
  url = {https://ml2.inf.ethz.ch/papers/2012/pletscher2012lpqp.pdf}
}
Ortega, P., Grau-Moya, J., Genewein, T., Balduzzi, D. & Braun, D. A Nonparametric Conjugate Prior Distribution for the Maximizing Argument of a Noisy Function 2012   inproceedings  
BibTeX:
@inproceedings{rtg2012,
  author = {Ortega, Pedro and Grau-Moya, Jordi and Genewein, Tim and Balduzzi, David and Braun, Daniel},
  title = {{A} {N}onparametric {C}onjugate {P}rior {D}istribution for the {M}aximizing {A}rgument of a {N}oisy {F}unction},
  publisher = {MIT Press},
  year = {2012},
  volume = {25},
  pages = {3014--3022}
}
Vezhnevets, A., Buhmann, J. & Ferrari, V. Active Learning for Semantic Segmentation with Expected Change 2012 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   inproceedings DOI URL  
BibTeX:
@inproceedings{vezhnevets12cvpra,
  author = {Alexander Vezhnevets and Joachim Buhmann and Vittorio Ferrari},
  title = {Active Learning for Semantic Segmentation with Expected Change},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) },
  year = {2012},
  url = {http://www.inf.ethz.ch/personal/vezhneva/Pubs/VezhnevetsCVPR2012a.pdf},
  doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248050}
}
Vezhnevets, A., Ferrari, V. & Buhmann, J. Weakly Supervised Structured Output Learning for Semantic Segmentation 2012 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   inproceedings DOI URL  
BibTeX:
@inproceedings{vezhnevets12cvprb,
  author = {Alexander Vezhnevets and Vittorio Ferrari and Joachim Buhmann},
  title = {Weakly Supervised Structured Output Learning for Semantic Segmentation},
  booktitle = { Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) },
  year = {2012},
  url = {http://www.inf.ethz.ch/personal/vezhneva/Pubs/VezhnevetsCVPR2012b.pdf},
  doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6247757}
}
Zhong, Q., Busetto, A. G., Fededa, J. P., Buhmann, J. M. & Gerlich, D. W. Unsupervised modeling of cell morphology dynamics for time-lapse microscopy 2012 Nature Methods   article DOI URL  
Abstract: Analysis of cellular phenotypes in large imaging data sets conventionally involves supervised statistical methods, which require user-annotated training data. This paper introduces an unsupervised learning method, based on temporally constrained combinatorial clustering, for automatic prediction of cell morphology classes in time-resolved images. We applied the unsupervised method to diverse fluorescent markers and screening data and validated accurate classification of human cell phenotypes, demonstrating fully objective data labeling in image-based systems biology.
BibTeX:
@article{,
  author = {Zhong, Qing and Busetto, Alberto Giovanni and Fededa, Juan P. and Buhmann, Joachim M. and Gerlich, Daniel W.},
  title = {Unsupervised modeling of cell morphology dynamics for time-lapse microscopy},
  journal = {Nature Methods},
  year = {2012},
  volume = {advance online publication},
  url = {http://www.nature.com/nmeth/journal/vaop/ncurrent/full/nmeth.2046.html},
  doi = {10.1038/nmeth.2046}
}
Vezhnevets, A. & Buhmann, J. M. Agnostic domain adaptation 2011 Proceedings of the 33rd international conference on Pattern recognition   inproceedings URL  
BibTeX:
@inproceedings{AV:JB:DAGM:2011,
  author = {Vezhnevets, Alexander and Buhmann, Joachim M.},
  title = {Agnostic domain adaptation},
  booktitle = {Proceedings of the 33rd international conference on Pattern recognition},
  publisher = {Springer-Verlag},
  year = {2011},
  pages = {376--385},
  url = {http://dl.acm.org/citation.cfm?id=2039976.2040022}
}
Bicego, M., Ulas, A., Schüffler, P., Castellani, U., Murino, V., Martins, A., Aguiar, P. & Figueiredo, M. Renal Cancer Cell Classification Using Generative Embeddings and Information Theoretic Kernels 2011 IAPR/PRIB   inproceedings  
BibTeX:
@inproceedings{bicego2011,
  author = {Manuele Bicego and Aydin Ulas and Peter Sch\"uffler and Umberto Castellani and Vittorio Murino and Andrè Martins and Pedro Aguiar and Mario Figueiredo},
  title = {Renal Cancer Cell Classification Using Generative Embeddings and Information Theoretic Kernels},
  booktitle = {IAPR/PRIB},
  year = {2011}
}
E., A. & H., B. Biological Network Determination with Application to Keratinocyte Migration Control 2011 The 8th International Workshop on Computational Systems Biology (WCSB 2011)   inproceedings  
BibTeX:
@inproceedings{Bionetdet,
  author = {August E.~and Busch H.},
  title = {Biological Network Determination with Application to Keratinocyte Migration Control},
  booktitle = {The 8th International Workshop on Computational Systems Biology (WCSB 2011)},
  year = {2011}
}
Brodersen, K. H., Schofield, T. M., Leff, A. P., Ong, C. S., Lomakina, E. I., Buhmann, J. M. & Stephan, K. E. Generative Embedding for Model-Based Classification of fMRI Data 2011 PLoS Comput Biol   article DOI URL  
Abstract: Decoding models, such as those underlying multivariate classification algorithms, have been increasingly used to infer cognitive or clinical brain states from measures of brain activity obtained by functional magnetic resonance imaging (fMRI). The practicality of current classifiers, however, is restricted by two major challenges. First, due to the high data dimensionality and low sample size, algorithms struggle to separate informative from uninformative features, resulting in poor generalization performance. Second, popular discriminative methods such as support vector machines (SVMs) rarely afford mechanistic interpretability. In this paper, we address these issues by proposing a novel generative-embedding approach that incorporates neurobiologically interpretable generative models into discriminative classifiers. Our approach extends previous work on trial-by-trial classification for electrophysiological recordings to subject-by-subject classification for fMRI and offers two key advantages over conventional methods: it may provide more accurate predictions by exploiting discriminative information encoded in ‘hidden’ physiological quantities such as synaptic connection strengths; and it affords mechanistic interpretability of clinical classifications. Here, we introduce generative embedding for fMRI using a combination of dynamic causal models (DCMs) and SVMs. We propose a general procedure of DCM-based generative embedding for subject-wise classification, provide a concrete implementation, and suggest good-practice guidelines for unbiased application of generative embedding in the context of fMRI. We illustrate the utility of our approach by a clinical example in which we classify moderately aphasic patients and healthy controls using a DCM of thalamo-temporal regions during speech processing. Generative embedding achieves a near-perfect balanced classification accuracy of 98% and significantly outperforms conventional activation-based and correlation-based methods. This example demonstrates how disease states can be detected with very high accuracy and, at the same time, be interpreted mechanistically in terms of abnormalities in connectivity. We envisage that future applications of generative embedding may provide crucial advances in dissecting spectrum disorders into physiologically more well-defined subgroups.
BibTeX:
@article{brodersen_generative_2011,
  author = {Brodersen, Kay H. and Schofield, Thomas M. and Leff, Alexander P. and Ong, Cheng Soon and Lomakina, Ekaterina I. and Buhmann, Joachim M. and Stephan, Klaas E.},
  title = {Generative Embedding for {Model-Based} Classification of {fMRI} Data},
  journal = {{PLoS} Comput Biol},
  year = {2011},
  volume = {7},
  number = {6},
  pages = {e1002079},
  url = {http://dx.doi.org/10.1371/journal.pcbi.1002079},
  doi = {10.1371/journal.pcbi.1002079}
}
Brodersen, K. H., Haiss, F., Ong, C. S., Jung, F., Tittgemeyer, M., Buhmann, J. M., Weber, B. & Stephan, K. E. Model-based feature construction for multivariate decoding 2011 NeuroImage   article DOI URL  
Abstract: Conventional decoding methods in neuroscience aim to predict discrete brain states from multivariate correlates of neural activity. This approach faces two important challenges. First, a small number of examples are typically represented by a much larger number of features, making it hard to select the few informative features that allow for accurate predictions. Second, accuracy estimates and information maps often remain descriptive and can be hard to interpret. In this paper, we propose a model-based decoding approach that addresses both challenges from a new angle. Our method involves (i) inverting a dynamic causal model of neurophysiological data in a trial-by-trial fashion; (ii) training and testing a discriminative classifier on a strongly reduced feature space derived from trial-wise estimates of the model parameters; and (iii) reconstructing the separating hyperplane. Since the approach is model-based, it provides a principled dimensionality reduction of the feature space; in addition, if the model is neurobiologically plausible, decoding results may offer a mechanistically meaningful interpretation. The proposed method can be used in conjunction with a variety of modelling approaches and brain data, and supports decoding of either trial or subject labels. Moreover, it can supplement evidence-based approaches for model-based decoding and enable structural model selection in cases where Bayesian model selection cannot be applied. Here, we illustrate its application using dynamic causal modelling (DCM) of electrophysiological recordings in rodents. We demonstrate that the approach achieves significant above-chance performance and, at the same time, allows for a neurobiological interpretation of the results.
BibTeX:
@article{brodersen_model-based_2011,
  author = {Kay H. Brodersen and Florent Haiss and Cheng Soon Ong and Fabienne Jung and Marc Tittgemeyer and Joachim M. Buhmann and Bruno Weber and Klaas E. Stephan},
  title = {Model-based feature construction for multivariate decoding},
  journal = {{NeuroImage}},
  year = {2011},
  volume = {56},
  number = {2},
  pages = {601--615},
  url = {http://www.sciencedirect.com/science/article/B6WNP-4YWB2FG-2/2/f5c5d7fbafcee87aa70ff3fa1ffaa270},
  doi = {10.1016/j.neuroimage.2010.04.036}
}
Busse, L. M. & Buhmann, J. M. Model-Based Clustering of Inhomogeneous Paired Comparison Data 2011 Similarity-Based Pattern Recognition, Lecture Notes in Computer Science Volume 7005   inproceedings  
BibTeX:
@inproceedings{bussel2011a,
  author = {Ludwig M. Busse and Joachim M. Buhmann},
  title = {Model-Based Clustering of Inhomogeneous Paired Comparison Data},
  booktitle = {Similarity-Based Pattern Recognition, Lecture Notes in Computer Science Volume 7005},
  year = {2011},
  pages = {207--221}
}
Busse, L. M., Chehreghani, M. H. & Buhmann, J. M. Approximate Sorting (of Preference Data) 2011 NIPS Workshop on Choice Models and Preference Learning   unpublished  
BibTeX:
@unpublished{bussel2011b,
  author = {Ludwig M. Busse and Morteza Haghir Chehreghani and Joachim M. Buhmann},
  title = {Approximate Sorting (of Preference Data)},
  booktitle = {NIPS Workshop on Choice Models and Preference Learning},
  year = {2011}
}
Floros, X., Bergero, F., Cellier, F. E. & Kofman, E. Automated Simulation of Modelica Models with QSS Methods : The Discontinuous Case 2011 8th International Modelica Conference 2011, Dresden, Germany   inproceedings DOI URL  
Abstract: This study describes the current implementation of an interface that automatically translates a discontinuous model described using the Modelica language into the Discrete Event System Specification (DEVS) formalism. More specifically, the interface enables the automatic simulation of a Modelica model with discontinuities in the PowerDEVS environment, where the Quantized State Systems (QSS) integration methods are implemented. Providing DEVS-based simulation algorithms to Modelica users should extend significantly the tools that are currently available in order to efficiently simulate several classes of largescale real-world problems, e.g. systems with heavy discontinuities. In this work both the theoretical design and the implementation of the interface are discussed. Furthermore, simulation results are provided that demonstrate the correctness of the proposed implementation as well as the superior performance of QSS methods when simulating discontinuous systems.
BibTeX:
@inproceedings{florosx_2011,
  author = {Xenofon Floros and Federico Bergero and Fran\c{c}ois E. Cellier and Ernesto Kofman},
  title = {Automated Simulation of Modelica Models with QSS Methods : The Discontinuous Case},
  booktitle = {8th International Modelica Conference 2011, Dresden, Germany},
  publisher = {Linköping University Electronic Press, Linköpings universitet},
  year = {2011},
  pages = {657-667},
  url = {https://www.modelica.org/events/modelica2011/Proceedings/pages/papers/47_1_ID_148_a_fv.pdf},
  doi = {10.3384/ecp11063657}
}
Mehmet Gnen, Aydin Ulas, P. J. S. U. C. & Murino, V. Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma 2011 SIMBAD 2011 workshop   inproceedings  
BibTeX:
@inproceedings{goenen2011,
  author = {Mehmet G\"önen, Aydin Ulas, Peter J. Sch\"uffler, Umberto Castellani and Vittorio Murino},
  title = {Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma},
  booktitle = {SIMBAD 2011 workshop},
  year = {2011}
}
Sunehag, P. & Hutter, M. Axioms for Rational Reinforcement Learning 2011 Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT'11)   inproceedings DOI URL PDF  
Abstract: We provide a formal, simple and intuitive theory of rational decision making including sequential decisions that affect the environment. The theory has a geometric flavor, which makes the arguments easy to visualize and understand. Our theory is for complete decision makers, which means that they have a complete set of preferences. Our main result shows that a complete rational decision maker implicitly has a probabilistic model of the environment. We have a countable version of this result that brings light on the issue of countable vs finite additivity by showing how it depends on the geometry of the space which we have preferences over. This is achieved through fruitfully connecting rationality with the Hahn-Banach Theorem. The theory presented here can be viewed as a formalization and extension of the betting odds approach to probability of Ramsey (1931) and De Finetti (1937).
BibTeX:
@inproceedings{Hutter:11aixiaxiom,
  author = {Peter Sunehag and Marcus Hutter},
  title = {Axioms for Rational Reinforcement Learning},
  booktitle = {Proc. 22nd International Conf. on Algorithmic Learning Theory ({ALT'11})},
  publisher = {Springer, Berlin},
  year = {2011},
  volume = {6925},
  pages = {338--352},
  url = {http://arxiv.org/abs/1107.5520},
  doi = {10.1007/978-3-642-24412-4_27}
}
Lattimore, T. & Hutter, M. Asymptotically Optimal Agents 2011 Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT'11)   inproceedings DOI URL PDF  
Abstract: Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.
BibTeX:
@inproceedings{Hutter:11asyoptag,
  author = {Tor Lattimore and Marcus Hutter},
  title = {Asymptotically Optimal Agents},
  booktitle = {Proc. 22nd International Conf. on Algorithmic Learning Theory ({ALT'11})},
  publisher = {Springer, Berlin},
  year = {2011},
  volume = {6925},
  pages = {368--382},
  url = {http://arxiv.org/abs/1107.5537},
  doi = {10.1007/978-3-642-24412-4_29}
}
Lattimore, T., Hutter, M. & Gavane, V. Universal Prediction of Selected Bits 2011 Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT'11)   inproceedings DOI URL PDF  
Abstract: Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the target data given input data and previous input/target pairs. Solomonoff induction is known to solve the general sequence prediction problem, but only if the entire sequence is sampled from a computable distribution. In the case of classification and discriminative learning though, only the targets need be structured (given the inputs). We show that the normalised version of Solomonoff induction can still be used in this case, and more generally that it can detect any recursive sub-pattern (regularity) within an otherwise completely unstructured sequence. It is also shown that the unnormalised version can fail to predict very simple recursive sub-patterns.
BibTeX:
@inproceedings{Hutter:11evenbits,
  author = {Tor Lattimore and Marcus Hutter and Vaibhav Gavane},
  title = {Universal Prediction of Selected Bits},
  booktitle = {Proc. 22nd International Conf. on Algorithmic Learning Theory ({ALT'11})},
  publisher = {Springer, Berlin},
  year = {2011},
  volume = {6925},
  pages = {262--276},
  url = {http://arxiv.org/abs/1107.5531},
  doi = {10.1007/978-3-642-24412-4_22}
}
Lattimore, T. & Hutter, M. Time Consistent Discounting 2011 Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT'11)   inproceedings DOI URL PDF  
Abstract: A possibly immortal agent tries to maximise its summed discounted rewards over time, where discounting is used to avoid infinite utilities and encourage the agent to value current rewards more than future ones. Some commonly used discount functions lead to time-inconsistent behavior where the agent changes its plan over time. These inconsistencies can lead to very poor behavior. We generalise the usual discounted utility model to one where the discount function changes with the age of the agent. We then give a simple characterisation of time-(in)consistent discount functions and show the existence of a rational policy for an agent that knows its discount function is time-inconsistent.
BibTeX:
@inproceedings{Hutter:11tcdisc,
  author = {Tor Lattimore and Marcus Hutter},
  title = {Time Consistent Discounting},
  booktitle = {Proc. 22nd International Conf. on Algorithmic Learning Theory ({ALT'11})},
  publisher = {Springer, Berlin},
  year = {2011},
  volume = {6925},
  pages = {383--397},
  url = {http://arxiv.org/abs/1107.5528},
  doi = {10.1007/978-3-642-24412-4_30}
}
Cima, I., Schiess, R., Wild, P., Kaelin, M., Schüffler, P., Lange, V., Picotti, P., Ossola, R., Templeton, A., Schubert, O., Fuchs, T., Leippold, T., Wyler, S., Zehetner, J., Jochum, W., Buhmann, J. M., Cerny, T., Moch, H., Gillessen, S., Aebersold, R. & Krek, W. Cancer genetics-guided discovery of serum biomarker signatures for diagnosis and prognosis of prostate cancer 2011 Proceedings of the National Academy of Sciences USA   article DOI URL  
BibTeX:
@article{IC:etal:PNAS:11,
  author = {Igor Cima and Ralph Schiess and Peter Wild and Martin Kaelin and Peter Sch{\"u}ffler and Vinzenz Lange and Paola Picotti and Reto Ossola and Arnoud Templeton and Olga Schubert and Thomas Fuchs and Thomas Leippold and Stephen Wyler and Jens Zehetner and Wolfram Jochum and Joachim M. Buhmann and Thomas Cerny and Holger Moch and Silke Gillessen and Ruedi Aebersold and Wilhelm Krek},
  title = {Cancer genetics-guided discovery of serum biomarker signatures for diagnosis and prognosis of prostate cancer},
  journal = {Proceedings of the National Academy of Sciences USA},
  year = {2011},
  volume = {108},
  number = {8},
  pages = {3342-3347},
  url = {http://www.pnas.org/content/108/8/3342.abstract},
  doi = {10.1073/pnas.1013699108}
}
Buhmann, J. M. Context sensitive information: Model validation by information theory 2011 MCPR 2011   inproceedings  
Abstract: A theory of patterns analysis has to provide a criterion to filter out the relevant information to identify patterns. The set of potential patterns, also called hypothesis class of the problem, defines admissible explanations of the available data and it specifies the context for a patterns analysis task. Fluctuations in the measurements limit the precision which we can achieve to identify such patterns. Effectively, the distinguishable patterns define a code in a fictitious communication scenario where the selected cost function together with a stochastic data source plays the role of a noisy ``channel''. Maximizing the capacity of this channel determines the penalized costs of the pattern analysis problem with a data dependent regularization strength. The tradeoff between informativeness and robustness in statistical inference is mirrored in the balance between high information rate and zero communication error, thereby giving rise to a new notion of context sensitive information.
BibTeX:
@inproceedings{JB:mcpr:2011,
  author = {Joachim M. Buhmann},
  title = {Context sensitive information: Model validation by information theory},
  booktitle = {MCPR 2011},
  publisher = {Springer},
  year = {2011},
  volume = {6718},
  pages = {21-21}
}
Claassen, M., Reiter, L., Hengartner, M. O., Buhmann, J. M. & Aebersold, R. Generic comparison of protein inference engines 2011 Molecular & Cellular Proteomics   article DOI URL  
Abstract: Protein identifications, instead of peptide-spectrum matches, constitute the biologically relevant result of shotgun proteomics studies. How to appropriately infer and report protein identifications has triggered a still ongoing debate. This debate has so far suffered from the lack of appropriate performance measures that allow to objectively assess protein inference approaches. This study describes an intuitive, generic and yet formal performance measure and demonstrates how it enables experimentalists to select an optimal protein inference strategy for a given collection of fragment ion spectra. We applied the performance measure to systematically explore the benefit of excluding possibly unreliable protein identifications, such as single hit wonders. Therefore, we defined a family of protein inference engines, by extending a simple inference engine by thousands of pruning variants, each excluding a different specified set of possibly unreliable identifications. We benchmarked these protein inference engines on several datasets representing different proteomes and mass spectrometrical platforms. Optimally performing inference engines retained all high confidence spectral evidence, without posterior exclusion of any type of protein identifications. Despite the diversity of studied datasets consistently supporting this rule, other datasets might behave differently. In order to ensure maximal reliable proteome coverage for datasets arising in other studies, we advocate to abstain from rigid protein inference rules, like exclusion of single hit wonders, and instead to consider several protein inference approaches and to assess these with respect to the presented performance measure in the specific application context.
BibTeX:
@article{MC:LR:MH:JB:RA:RECOMB_satellite:2011,
  author = {Claassen, Manfred and Reiter, Lukas and Hengartner, Michael O. and Buhmann, Joachim M. and Aebersold, Ruedi},
  title = {Generic comparison of protein inference engines},
  journal = {Molecular \& Cellular Proteomics},
  year = {2011},
  url = {http://www.mcponline.org/content/early/2011/11/04/mcp.O110.007088.abstract},
  doi = {10.1074/mcp.O110.007088}
}
Frank, M. & Buhmann, J. M. Selecting the rank of SVD by Maximum Approximation Capacity 2011 International Symposium on Information Theory, St. Petersburg   inproceedings DOI  
Abstract: Truncated Singular Value Decomposition (SVD) calculates the closest rank-k approximation of a given input matrix. Selecting the appropriate rank k defines a critical model order choice in most applications of SVD. To obtain a principled cut-off criterion for the spectrum, we convert the underlying optimization problem into a noisy channel coding problem. The optimal approximation capacity of this channel controls the appropriate strength of regularization to suppress noise. In simulation experiments, this information theoretic method to determine the optimal rank competes with state-of-the art model selection techniques.
BibTeX:
@inproceedings{MF:JB:ISIT:2011,
  author = {Mario Frank and Joachim M. Buhmann},
  title = {Selecting the rank of SVD by Maximum Approximation Capacity},
  booktitle = {International Symposium on Information Theory, St. Petersburg},
  publisher = {IEEE},
  year = {2011},
  pages = {1036 - 1040},
  doi = {10.1109/ISIT.2011.6033687}
}
Frank, M., Chehreghani, M. & Buhmann, J. The Minimum Transfer Cost Principle for Model-Order Selection 2011 Machine Learning and Knowledge Discovery in Databases   incollection URL  
BibTeX:
@incollection{MF:MC:JMB:ECML:2011,
  author = {Frank, Mario and Chehreghani, Morteza and Buhmann, Joachim},
  title = {The Minimum Transfer Cost Principle for Model-Order Selection},
  booktitle = {Machine Learning and Knowledge Discovery in Databases},
  publisher = {Springer Berlin / Heidelberg},
  year = {2011},
  volume = {6911},
  pages = {423-438},
  note = {10.1007/978-3-642-23780-5\_37},
  url = {http://dx.doi.org/10.1007/978-3-642-23780-5\_37}
}
Peter Schüffler, Aydin Ulas, U. C. & Murino, V. A Multiple Kernel Learning Algorithm for Cell Nucleus Classification of Renal Cell Carcinoma 2011 ICIAP 2011   inproceedings  
BibTeX:
@inproceedings{PeterSchueffler2011,
  author = {Peter Sch\"uffler, Aydin Ulas, Umberto Castellani and Vittorio Murino},
  title = {A Multiple Kernel Learning Algorithm for Cell Nucleus Classification of Renal Cell Carcinoma},
  booktitle = {ICIAP 2011},
  year = {2011}
}
Pletscher, P., Nowozin, S., Kohli, P. & Rother, C. Putting MAP back on the map 2011 33rd Annual Symposium of the German Association for Pattern Recognition (DAGM)   inproceedings URL  
BibTeX:
@inproceedings{Pletscher2011,
  author = {Pletscher, Patrick and Nowozin, Sebastian and Kohli, Pushmeet and Rother, Carsten},
  title = {Putting MAP back on the map},
  booktitle = {33rd Annual Symposium of the German Association for Pattern Recognition ({DAGM})},
  year = {2011},
  url = {http://research.microsoft.com/en-us/um/people/pkohli/papers/pnkr_dagm2011.pdf}
}
Pletscher, P. & Wulff, S. A Combined LP and QP Relaxation for MAP 2011 NIPS Workshop on Discrete Optimization in Machine Learning (DISCML)   inproceedings URL  
BibTeX:
@inproceedings{Pletscher2011a,
  author = {Pletscher, Patrick and Wulff, Sharon},
  title = {A Combined LP and QP Relaxation for MAP},
  booktitle = {NIPS Workshop on Discrete Optimization in Machine Learning (DISCML)},
  year = {2011},
  url = {http://www.pletscher.org/papers/pletscher2011lpqp.pdf}
}
Peter Schüffler, Aydin Ulas, U. C. & Murino, V. A Multiple Kernel Learning Algorithm for Cell Nucleus Classification of Renal Cell Carcinoma 2011 ICIAP 2011   inproceedings  
BibTeX:
@inproceedings{schueffler2011,
  author = {Peter Sch\"uffler, Aydin Ulas, Umberto Castellani and Vittorio Murino},
  title = {A Multiple Kernel Learning Algorithm for Cell Nucleus Classification of Renal Cell Carcinoma},
  booktitle = {ICIAP 2011},
  year = {2011}
}
Fuchs, T. J. & Buhmann, J. M. Computational Pathology: Challenges and Promises for Tissue Analysis 2011 Computerized Medical Imaging and Graphics   article DOI URL  
Abstract: The histological assessment of human tissue has emerged as the key challenge for detection and treatment of cancer. A plethora of different data sources ranging from tissue microarray data to gene expression, proteomics or metabolomics data provide a detailed overview of the health status of a patient. Medical doctors need to assess these information sources and they rely on data driven automatic analysis tools. Methods for classification, grouping and segmentation of heterogeneous data sources as well as regression of noisy dependencies and estimation of survival probabilities enter the processing workflow of a pathology diagnosis system at various stages. This paper reports on state-of-the-art of the design and effectiveness of computational pathology workflows and it discusses future research directions in this emergent field of medical informatics and diagnostic machine learning.
BibTeX:
@article{TF:JMB:CMIG:2011,
  author = {Thomas J. Fuchs and Joachim M. Buhmann},
  title = {Computational Pathology: Challenges and Promises for Tissue Analysis},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2011},
  volume = {35},
  number = {7-8},
  pages = {515-530},
  url = {http://www.sciencedirect.com/science/article/pii/S0895611111000383},
  doi = {DOI: 10.1016/j.compmedimag.2011.02.006}
}
Ulas, A., Schüffler, P. J., Bicego, M., Castellani, U. & Murino, V. Hybrid Generative-Discriminative Nucleus Classification of Renal Cell Carcinoma 2011 SIMBAD 2011 workshop   inproceedings  
BibTeX:
@inproceedings{ulas2011,
  author = {Aydin Ulas and Peter J. Sch\"uffler and Manuele Bicego and Umberto Castellani and Vittorio Murino},
  title = {Hybrid Generative-Discriminative Nucleus Classification of Renal Cell Carcinoma},
  booktitle = {SIMBAD 2011 workshop},
  year = {2011}
}
Vezhnevets, A., Ferrari, V. & Buhmann, J. Weakly Supervised Semantic Segmentation with a Multi-image Model 2011 Proceedings of the International Conference on Computer Vision (ICCV)   inproceedings  
BibTeX:
@inproceedings{vezhnevets11iccv,
  author = {A. Vezhnevets and V. Ferrari and J. Buhmann},
  title = {Weakly Supervised Semantic Segmentation with a Multi-image Model},
  booktitle = {Proceedings of the International Conference on Computer Vision (ICCV)},
  year = {2011}
}
Lomakina, E., Brodersen, K., Behrens, T., Stephan, K. & Buhmann, J. Gaussian processes for whole-brain feature selection and classification in fMRI 2011 Interactive session at Human Brain Mapping 2011   inproceedings URL  
BibTeX:
@inproceedings{,
  author = {E.I. Lomakina and K.H. Brodersen and T.E.J. Behrens and K.E. Stephan and J.M. Buhmann},
  title = {Gaussian processes for whole-brain feature selection and classification in fMRI},
  booktitle = {Interactive session at Human Brain Mapping 2011},
  year = {2011},
  url = {http://people.inf.ethz.ch/bkay/publications/Lomakina_2011_HBM.pdf}
}
Krause, A. & Ong, C. S. Contextual Gaussian Process Bandit Optimization 2011 Advances in Neural Information Processing   article URL  
Abstract: How should we design experiments to maximize performance of a complex
system, taking into account uncontrollable environmental conditions? How
should we select relevant documents (ads) to display, given information about the
user? These tasks can be formalized as contextual bandit problems, where at each
round, we receive context (about the experimental conditions, the query), and
have to choose an action (parameters, documents). The key challenge is to trade
off exploration by gathering data for estimating the mean payoff function over the
context-action space, and to exploit by choosing an action deemed optimal based
on the gathered data. We model the payoff function as a sample from a Gaussian
process defined over the joint context-action space, and develop CGP-UCB, an
intuitive upper-confidence style algorithm. We show that by mixing and matching
kernels for contexts and actions, CGP-UCB can handle a variety of practical applications.
We further provide generic tools for deriving regret bounds when using
such composite kernel functions. Lastly, we evaluate our algorithm on two case
studies, in the context of automated vaccine design and sensor management. We
show that context-sensitive optimization outperforms no or naive use of context.
BibTeX:
@article{,
  author = {Andreas Krause and Cheng Soon Ong},
  title = {Contextual Gaussian Process Bandit Optimization},
  journal = {Advances in Neural Information Processing},
  year = {2011},
  url = {http://www.inf.ethz.ch/personal/cong/papers/krause11cgp-ucb.pdf}
}
Dinuzzo, F., Ong, C. S., Gehler, P. & Pillonetto, G. Learning Output Kernels with Block Coordinate Descent 2011 Proceedings of the International Conference on Machine Learning   inproceedings URL  
BibTeX:
@inproceedings{,
  author = {Francesco Dinuzzo and Cheng Soon Ong and Peter Gehler and and Gianluigi Pillonetto},
  title = {Learning Output Kernels with Block Coordinate Descent},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  year = {2011},
  url = {http://www.inf.ethz.ch/personal/cong/papers/dinuzzo11output-kernel.pdf}
}
Buhmann, J. M., Chehreghani, M. H., Frank, M. & Streich, A. P. Information Theoretic Model Selection for Pattern Analysis 2011 JMLR: Workshop and Conference Proceedings   inproceedings URL  
BibTeX:
@inproceedings{,
  author = {Joachim M. Buhmann and Morteza Haghir Chehreghani and Mario Frank and Andreas P. Streich},
  title = {Information Theoretic Model Selection for Pattern Analysis},
  booktitle = {JMLR: Workshop and Conference Proceedings},
  year = {2011},
  number = {7},
  pages = {1-15},
  url = {http://www.mariofrank.net/paper/ICML2011_ASC4patternAnalysis.pdf}
}
Baschera, G.-M., Busetto, A., Klingler, S., Buhmann, J. & Gross, M. Modeling Engagement Dynamics in Spelling Learning 2011 Proc. of the 15th Int. Conf. on Artificial Intelligence in Education (AIED 11)   inproceedings URL  
BibTeX:
@inproceedings{,
  author = {G.-M. Baschera and A.G. Busetto and S. Klingler and J.M. Buhmann and M. Gross},
  title = {Modeling Engagement Dynamics in Spelling Learning},
  booktitle = {Proc. of the 15th Int. Conf. on Artificial Intelligence in Education (AIED 11)},
  publisher = {Springer Lecture Notes in Computer Science},
  year = {2011},
  pages = {31-38},
  url = {http://www.springerlink.com/content/978-3-642-21868-2/}
}
August, E. & Barahona, M. Solutions of weakly reversible chemical reaction networks are bounded and persistent 2010 Proceedings of the 11th International Symposium on Computer Applications in Biotechnology (CAB 2010)   inproceedings URL  
Abstract: We present extensions to chemical reaction network theory which are relevant to
the analysis of models of biochemical systems. We show that, for positive initial conditions,
solutions of a weakly reversible chemical reaction network are bounded and remain in the
positive orthant. Thus, weak reversibility implies persistence as conjectured by Martin Feinberg.
Our result provides a qualitative criterion to establish that a biochemical network will not
diverge or converge to the boundary, where some concentration levels are zero. It relies on
checking structural properties of the graph of the reaction network solely. It can also be used to
characterise certain bifurcations from stationary to oscillatory behaviour. We illustrate the use
of our result through applications.
BibTeX:
@inproceedings{August2010CAB,
  author = {August, E. and Barahona, M.},
  title = {Solutions of weakly reversible chemical reaction networks are bounded and persistent},
  booktitle = {Proceedings of the 11th International Symposium on Computer Applications in Biotechnology (CAB 2010)},
  year = {2010},
  url = {http://www.nt.ntnu.no/users/skoge/prost/proceedings/dycops-2010/Papers_CAB2010_common/WeMT3-03.pdf}
}
Mélykúti, B., August, E., Papachristodoulou, A. & El-Samad, H. Discriminating between rival biochemical network models: three approaches to optimal experiment design 2010 BMC Systems Biology   article URL  
Abstract: Background:
The success of molecular systems biology hinges on the ability to use computational models to
design predictive experiments, and ultimately unravel underlying biological mechanisms. A problem commonly
encountered in the computational modelling of biological networks is that alternative, structurally different models
of similar complexity fit a set of experimental data equally well. In this case, more than one molecular mechanism
can explain available data. In order to rule out the incorrect mechanisms, one needs to invalidate incorrect models.
At this point, new experiments maximizing the difference between the measured values of alternative models
should be proposed and conducted. Such experiments should be optimally designed to produce data that are
most likely to invalidate incorrect model structures.
Results:
In this paper we develop methodologies for the optimal design of experiments with the aim of
discriminating between different mathematical models of the same biological system. The first approach
determines the ‘best’ initial condition that maximizes the L2 (energy) distance between the outputs of the rival
models. In the second approach, we maximize the L2-distance of the outputs by designing the optimal external
stimulus (input) profile of unit L2-norm. Our third method uses optimized structural changes (corresponding, for
example, to parameter value changes reflecting gene knock-outs) to achieve the same goal. The numerical
implementation of each method is considered in an example, signal processing in starving Dictyostelium amoebæ.
Conclusions:
Model-based design of experiments improves both the reliability and the efficiency of biochemical
network model discrimination. This opens the way to model invalidation, which can be used to perfect our
understanding of biochemical networks. Our general problem formulation together with the three proposed
experiment design methods give the practitioner new tools for a systems biology approach to experiment design.
BibTeX:
@article{AugustBMC2010,
  author = {Bence M{\'e}lyk{\'u}ti and Elias August and Antonis Papachristodoulou and Hana El-Samad},
  title = {Discriminating between rival biochemical network models: three approaches to optimal experiment design},
  journal = {BMC Systems Biology},
  year = {2010},
  volume = {4},
  pages = {38},
  url = {http://www.biomedcentral.com/1752-0509/4/38}
}
Papachristodoulou, A., Chang, Y., August, E. & Anderson, J. Simplifying Networked Systems with Guaranteed Error Bounds 2010 49th IEEE Conference on Decision and Control, Atlanta, GA, USA   inproceedings  
BibTeX:
@inproceedings{AugustCDC2010,
  author = {A Papachristodoulou and YC Chang and E August and J Anderson},
  title = {Simplifying Networked Systems with Guaranteed Error Bounds},
  booktitle = {49th IEEE Conference on Decision and Control, Atlanta, GA, USA},
  year = {2010}
}
Vezhnevets, A. & Buhmann, J. Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning 2010 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   inproceedings  
BibTeX:
@inproceedings{bb32888,
  author = {Vezhnevets, A. and Buhmann, J.M.},
  title = {Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2010},
  pages = {3249-3256}
}
Brodersen, K. H., Ong, C. S., Stephan, K. E. & Buhmann, J. M. The balanced accuracy and its posterior distribution 2010 Proceedings of the 20th International Conference on Pattern Recognition   inproceedings DOI  
Abstract: Evaluating the performance of a classification algorithm critically requires a measure of the degree to which unseen examples have been identified with their correct class labels. In practice, generalizability is frequently estimated by averaging the accuracies obtained on individual cross-validation folds. This procedure, however, is problematic in two ways. First, it does not allow for the derivation of meaningful confidence intervals. Second, it leads to an optimistic estimate when a biased classifier is tested on an imbalanced dataset. We show that both problems can be overcome by replacing the conventional point estimate of accuracy by an estimate of the posterior distribution of the balanced accuracy.
BibTeX:
@inproceedings{brodersen_balanced_2010,
  author = {Kay H. Brodersen and Cheng Soon Ong and K. E. Stephan and Joachim M Buhmann},
  title = {The balanced accuracy and its posterior distribution},
  booktitle = {Proceedings of the 20th International Conference on Pattern Recognition},
  publisher = {{IEEE} Computer Society},
  year = {2010},
  pages = {3121--3124},
  doi = {10.1109/ICPR.2010.764}
}
Brodersen, K. H., Ong, C. S., Stephan, K. E. & Buhmann, J. M. The binormal assumption on precision-recall curves 2010 Proceedings of the 20th International Conference on Pattern Recognition   inproceedings DOI  
Abstract: The precision-recall curve (PRC) has become a widespread conceptual basis for assessing classification performance. The curve relates the positive predictive value of a classifier to its true positive rate and often provides a useful alternative to the well-known receiver operating characteristic (ROC). The empirical PRC, however, turns out to be a highly imprecise estimate of the true curve, especially in the case of a small sample size and class imbalance in favour of negative examples. Ironically, this situation tends to occur precisely in those applications where the curve would be most useful, e.g., in anomaly detection or information retrieval. Here, we propose to estimate the PRC on the basis of a simple distributional assumption about the decision values that generalizes the established binormal model for estimating smooth ROC curves. Using simulations, we show that our approach outperforms empirical estimates, and that an account of the class imbalance is crucial for obtaining unbiased PRC estimates.
BibTeX:
@inproceedings{brodersen_binormal_2010,
  author = {Kay H. Brodersen and Cheng Soon Ong and K. E. Stephan and Joachim M Buhmann},
  title = {The binormal assumption on precision-recall curves},
  booktitle = {Proceedings of the 20th International Conference on Pattern Recognition},
  publisher = {{IEEE} Computer Society},
  year = {2010},
  pages = {4263--4266},
  doi = {10.1109/ICPR.2010.1036}
}
Claassen, M., Aebersold, R. & Buhmann, J. M. Proteome Coverage Prediction for Integrated Proteomics Datasets 2010 RECOMB   article  
BibTeX:
@article{CAB09multi,
  author = {Claassen, M. and Aebersold, R. and Buhmann, J. M.},
  title = {{Proteome Coverage Prediction for Integrated Proteomics Datasets}},
  journal = {RECOMB},
  year = {2010},
  volume = {accepted}
}
Claassen, M., Reiter, L., Hengartner, M. O., Buhmann, J. M. & Aebersold, R. Generic Comparison of Protein Inference Engine Families 2010 RECOMB Satellite Conference on Computational Proteomics   inproceedings  
BibTeX:
@inproceedings{CRHBA10,
  author = {Claassen, Manfred and Reiter, Lukas and Hengartner, Michael O. and Buhmann, Joachim M. and Aebersold, Ruedi},
  title = {Generic Comparison of Protein Inference Engine Families},
  journal = {RECOMB Satellite Conference on Computational Proteomics},
  year = {2010}
}
Sigg, C. D., Dikk, T. & Buhmann, J. M. Speech Enhancement with Sparse Coding in Learned Dictionaries 2010 Proceedings of 35th IEEE International Conference on Acoustics, Speech and Signal Processing   inproceedings PDF  
BibTeX:
@inproceedings{CSTD10,
  author = {Christian D. Sigg and Tomas Dikk and Joachim M. Buhmann},
  title = {Speech Enhancement with Sparse Coding in Learned Dictionaries},
  booktitle = {Proceedings of 35th IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2010}
}
Floros, X., Cellier, F. & Kofman, E. Discretizing Time or States? A Comparative Study between DASSL and QSS 2010 3rd International Workshop on Equation-Based Object-Oriented Modeling Languages and Tools, EOOLT, Oslo, Norway, October 3, 2010   inproceedings  
Abstract: In this study, a system is presented and analyzed that automatically translates a model described within the Modelica framework into the Discrete Event System Specification (DEVS) formalism.

More specifically, this work interfaces the open-source implementation of Modelica, OpenModelica, and one particular software tool for DEVS modeling and simulation, the PowerDEVS environment, which implements the Quantized State Systems (QSS) integration methods introduced by Kofman.

The interface enables the automatic simulation of large-scale models with both DASSL (using the OpenModelica run-time environment) and QSS (using PowerDEVS) and extracts features, such as accuracy and simulation time, that allow a quantitative comparison of these integration methods. In this way, meaningful insight can be obtained on their respective advantages and disadvantages when used for simulating real-world applications.
Furthermore, the implemented interface allows any user without any knowledge of DEVS and/or QSS methods to simulate their systems in PowerDEVS by supplying a Modelica model as input only.

BibTeX:
@inproceedings{Floros2010,
  author = {Xenofon Floros and Francois Cellier and Ernesto Kofman},
  title = {Discretizing Time or States? A Comparative Study between DASSL and QSS},
  booktitle = {3rd International Workshop on Equation-Based Object-Oriented Modeling Languages and Tools, EOOLT, Oslo, Norway, October 3, 2010},
  year = {2010},
  pages = {107-115}
}
Buhmann, J. M. Information theoretic model validation for clustering 2010 International Symposium on Information Theory, Austin Texas   proceedings PDF  
Abstract: Model selection in clustering requires (i) to specify a suitable clustering principle and (ii) to control the model order complexity by choosing an appropriate number of clusters depending on the noise level in the data. We advocate an information theoretic perspective where the uncertainty in the measurements quantizes the set of data partitionings and, thereby, induces uncertainty in the solution space of clusterings. A clustering model, which can tolerate a higher level of fluctuations in the measurements than alternative models, is considered to be superior provided that the clustering solution is equally informative. This tradeoff between informativeness and robustness is used as a model selection criterion. The requirement that data partitionings should generalize from one data set to an equally probable second data set gives rise to a new notion of structure induced information.
BibTeX:
@proceedings{JB:ISIT:2010,
  author = {Joachim M. Buhmann},
  title = {Information theoretic model validation for clustering},
  booktitle = {International Symposium on Information Theory, Austin Texas},
  publisher = {IEEE},
  year = {2010},
  note = {(in press)}
}
Moh, Y. & Buhmann, J. Regularized Online Learning of Pseudometrics 2010 International Conference on Acoustics, Speech and Signal Processing   inproceedings  
BibTeX:
@inproceedings{Moh2010a,
  author = {Y Moh and J Buhmann},
  title = {Regularized Online Learning of Pseudometrics},
  booktitle = {International Conference on Acoustics, Speech and Signal Processing},
  year = {2010},
  pages = {1990-1993}
}
Orbanz, P. Construction of Nonparametric Bayesian Models from Parametric Bayes Equations 2010 Advances in Neural Information Processing Systems   inproceedings PDF  
Abstract: We consider the general problem of constructing nonparametric Bayesian models on infinite-dimensional random objects, such as functions, infinite graphs or infinite permutations. The problem has generated much interest in machine learning, where it is treated heuristically, but has not been studied in full generality in nonparametric Bayesian statistics, which tends to focus on models over probability distributions. Our approach applies a standard tool of stochastic process theory, the construction of stochastic processes from their finite-dimensional marginal distributions. The main contribution of the paper is a generalization of the classic Kolmogorov extension theorem to conditional probabilities. This extension allows a rigorous construction of nonparametric Bayesian models from systems of finitedimensional, parametric Bayes equations. Using this approach, we show (i) how existence of a conjugate posterior for the nonparametric model can be guaranteed by choosing conjugate finite-dimensional models in the construction, (ii) how the mapping to the posterior parameters of the nonparametric model can be explicitly determined, and (iii) that the construction of conjugate models in essence requires the finite-dimensional models to be in the exponential family. As an application of our constructive framework, we derive a model on infinite permutations, the nonparametric Bayesian analogue of a model recently proposed for the analysis of rank data.
BibTeX:
@inproceedings{Orbanz:2010,
  author = {P. Orbanz},
  title = {Construction of Nonparametric {B}ayesian Models from Parametric {B}ayes Equations},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2010},
  volume = {22}
}
Pletscher, P., Ong, C. S. & Buhmann, J. M. Entropy and Margin Maximization for Structured Output Learning 2010 Proceedings of the 20th European Conference on Marchine Learning (ECML)   inproceedings  
BibTeX:
@inproceedings{Pletscher:MaxEntMarg:2010,
  author = {Pletscher, Patrick and Ong, Cheng Soon and Buhmann, Joachim M.},
  title = {Entropy and Margin Maximization for Structured Output Learning},
  booktitle = {Proceedings of the 20th European Conference on Marchine Learning ({ECML})},
  year = {2010}
}
Frank, M., Buhmann, J. M. & Basin, D. On the definition of role mining 2010 SACMAT '10: Proceeding of the 15th ACM symposium on Access control models and technologies   inproceedings DOI URL  
Abstract: On the Definition of Role Mining

There have been many approaches proposed for role mining.
However, the problems solved often differ due to a lack of
consensus on the formal definition of the role mining problem.
In this paper, we provide a detailed analysis of the
requirements for role mining, the existing definitions of
role mining, and the methods used to assess role mining
results.
Given basic assumptions on how access-control
configurations are generated, we propose a novel definition
of the role mining problem that fulfills the requirements
that real-world enterprises typically have. In this way,
we recast role mining as a prediction problem.

BibTeX:
@inproceedings{SACMAT2010_DefinitionOfRoleMining,
  author = {Frank, Mario and Buhmann, Joachim M. and Basin, David},
  title = {On the definition of role mining},
  booktitle = {SACMAT '10: Proceeding of the 15th {ACM} symposium on Access control models and technologies},
  publisher = {ACM},
  year = {2010},
  pages = {35--44},
  url = {http://www.inf.ethz.ch/personal/mafrank/paper/DefOfRoleMining_SACMAT2010.pdf},
  doi = {http://doi.acm.org/10.1145/1809842.1809851}
}
Schüffler, P. J., Fuchs, T. J., Ong, C. S., Roth, V. & Buhmann, J. M. Computational TMA analysis and cell nucleus classification of renal cell carcinoma 2010 Pattern Recognition   inproceedings  
BibTeX:
@inproceedings{SchuefflerDAGM2010,
  author = {Peter J. Sch{\"u}ffler and Thomas J. Fuchs and Cheng Soon Ong and Volker Roth and Joachim M. Buhmann},
  title = {Computational TMA analysis and cell nucleus classification of renal cell carcinoma},
  booktitle = {Pattern Recognition},
  publisher = {Springer},
  year = {2010},
  pages = {202-211}
}
Streich, A. P., Feilner, M., Stirnemann, A. & Buhmann, J. M. Sound Field Indicators for Hearing Activity and Reverberation Time Estimation in Hearing Instruments 2010 AES 12th Convention   inproceedings  
Abstract: Sound field indicators (SFI) are proposed as a new feature set to estimate the hearing activity and reverberation time in hearing instruments. SFIs are based on physical measurements of the sound field. A variant thereof, called SFI short-time statistics SFIst2, is obtained by computing mean and standard deviations of SFIs on 10 subframes. To show the utility of these feature sets for the mentioned prediction tasks, experiments are carried out on artificially reverberated recordings of a large variety of sounds encountered in daily life. In a classification scenario where the hearing activity is to be predicted, both SFI and SFIst2 yield clearly superior accuracy even compared to hand-tailored features used in state-of-the-art hearing instruments. For regression on the reverberation time, the SFI-based features yield a lower residual error than standard feature sets and reach the performance of specially designed features. The hearing activity classification is mainly based on the average of the SFIs, while the standard deviation over sub-window is used heavily to predict the reverberation time.
BibTeX:
@inproceedings{SFIpaper,
  author = {Andreas P. Streich and Manuela Feilner and Alfred Stirnemann and Joachim M. Buhmann},
  title = {Sound Field Indicators for Hearing Activity and Reverberation Time Estimation in Hearing Instruments},
  booktitle = {AES 12th Convention},
  year = {2010}
}
Kaynig, V., Fischer, B., Müller, E. & Buhmann, J. M. Fully Automatic Stitching and Distortion Correction of Transmission Electron Microscope Images 2010 Journal of Structural Biology   article  
BibTeX:
@article{VK:BF:EM:JB:JSB:2010,
  author = {Verena Kaynig and Bernd Fischer and Elisabeth M{\"u}ller and Joachim M. Buhmann},
  title = {Fully Automatic Stitching and Distortion Correction of Transmission Electron Microscope Images},
  journal = {Journal of Structural Biology},
  year = {2010},
  volume = {171},
  number = {2},
  pages = {163-173}
}
Kaynig, V., Fuchs, T. & Buhmann, J. M. Neuron Geometry Extraction by Perceptual Grouping in ssTEM Images 2010 CVPR   inproceedings  
BibTeX:
@inproceedings{VK:TF:JB:CVPR:2010,
  author = {Verena Kaynig and Thomas Fuchs and Joachim M. Buhmann},
  title = {Neuron Geometry Extraction by Perceptual Grouping in ssTEM Images},
  booktitle = {CVPR},
  year = {2010}
}
Kaynig, V., Fuchs, T. & Buhmann, J. M. Geometrical Consistent 3D Tracing of Neuronal Processes in ssTEM Data 2010 MICCAI   inproceedings  
BibTeX:
@inproceedings{VK:TF:JB:MICCAI:2010,
  author = {Verena Kaynig and Thomas Fuchs and Joachim M. Buhmann},
  title = {Geometrical Consistent 3D Tracing of Neuronal Processes in ssTEM Data},
  booktitle = {MICCAI},
  year = {2010}
}
Schuffler, P., Mikeska, T., Waha, A., Lengauer, T. & Bock, C. MethMarker: user-friendly design and optimization of gene-specific DNA methylation assays 2009 Genome Biol   article URL  
Abstract: ABSTRACT: DNA methylation is a key mechanism of epigenetic regulation that is frequently altered in diseases such as cancer. To confirm the biological or clinical relevance of such changes, gene-specific DNA methylation changes need to be validated in multiple samples. We have developed the MethMarker http://methmarker.mpi-inf.mpg.de/ software to help design robust and cost-efficient DNA methylation assays for six widely used methods. Furthermore, MethMarker implements a bioinformatic workflow for transforming disease-specific differentially methylated genomic regions into robust clinical biomarkers.
BibTeX:
@article{schuefflermethmarker:2009,
  author = {Schuffler, P. and Mikeska, T. and Waha, A. and Lengauer, T. and Bock, C.},
  title = {MethMarker: user-friendly design and optimization of gene-specific DNA methylation assays},
  journal = {Genome Biol},
  year = {2009},
  volume = {10},
  number = {10},
  pages = {R105},
  note = {Journal article Genome biology Genome Biol. 2009 Oct 5;10(10):R105.},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/19804638?itool=EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_RVDocSum&ordinalpos=1}
}
Veeck, J., Wild, P. J., Fuchs, T., Schuffler, P. J., Hartmann, A., Knuchel, R. & Dahl, E. Prognostic relevance of Wnt-inhibitory factor-1 (WIF1) and Dickkopf-3 (DKK3) promoter methylation in human breast cancer 2009 BMC Cancer   article URL PDF  
Abstract: BACKGROUND: Secreted Wnt signaling antagonists have recently been described as frequent targets of epigenetic inactivation in human tumor entities. Since gene silencing of certain Wnt antagonists was found to be correlated with adverse patient survival in cancer, we aimed at investigating a potential prognostic impact of the two Wnt antagonizing molecules WIF1 and DKK3 in breast cancer, which are frequently silenced by promoter methylation in this disease. METHODS: WIF1 and DKK3 promoter methylation were assessed by methylation-specific PCR with bisulfite-converted DNA from 19 normal breast tissues and 150 primary breast carcinomas. Promoter methylation was interpreted in a qualitative, binary fashion. Statistical evaluations included two-sided Fisher's exact tests, univariate log-rank tests of Kaplan-Meier curves as well as multivariate Cox regression analyses. RESULTS: WIF1 and DKK3 promoter methylation were detected in 63.3% (95/150) and 61.3% (92/150) of breast carcinoma samples, respectively. In normal breast tissues, WIF1 methylation was present in 0% (0/19) and DKK3 methylation in 5.3% (1/19) of samples. In breast carcinomas, WIF1 methylation was significantly associated with methylation of DKK3 (p = 0.009). Methylation of either gene was not associated with clinicopathological parameters, except for DKK3 methylation being associated with patient age (p = 0.007). In univariate analysis, WIF1 methylation was not associated with clinical patient outcome. In contrast, DKK3 methylation was a prognostic factor in patient overall survival (OS) and disease-free survival (DFS). Estimated OS rates after 10 years were 54% for patients with DKK3-methylated tumors, in contrast to patients without DKK3 methylation in the tumor, who had a favorable 97% OS after 10 years (p < 0.001). Likewise, DFS at 10 years for patients harboring DKK3 methylation in the tumor was 58 compared with 78% for patients with unmethylated DKK3 (p = 0.037). Multivariate analyses revealed that DKK3 methylation was an independent prognostic factor predicting poor OS (hazard ratio (HR): 14.4; 95% confidence interval (CI): 1.9-111.6; p = 0.011), and short DFS (HR: 2.5; 95% CI: 1.0-6.0; p = 0.047) in breast cancer. CONCLUSION: Although the Wnt antagonist genes WIF1 and DKK3 show a very similar frequency of promoter methylation in human breast cancer, only DKK3 methylation proves as a novel prognostic marker potentially useful in the clinical management of this disease.
BibTeX:
@article{schuefflerprognostic:2009,
  author = {Veeck, J. and Wild, P. J. and Fuchs, T. and Schuffler, P. J. and Hartmann, A. and Knuchel, R. and Dahl, E.},
  title = {Prognostic relevance of Wnt-inhibitory factor-1 (WIF1) and Dickkopf-3 (DKK3) promoter methylation in human breast cancer},
  journal = {BMC Cancer},
  year = {2009},
  volume = {9},
  pages = {217},
  note = {Veeck, Jurgen Wild, Peter J Fuchs, Thomas Schuffler, Peter J Hartmann, Arndt Knuchel, Ruth Dahl, Edgar Research Support, Non-U.S. Gov't England BMC cancer BMC Cancer. 2009 Jul 1;9:217.},
  url = {http://www.ncbi.nlm.nih.gov/pubmed/19570204?itool=EntrezSystem2.PEntrez.Pubmed.Pubmed_ResultsPanel.Pubmed_RVDocSum&ordinalpos=2}
}
August, E. & Papachristodoulou, A. A new computational tool for establishing model parameter identifiability 2009 Journal of Computational Biology   article  
BibTeX:
@article{Anewcomp,
  author = {E.~August and A.~Papachristodoulou},
  title = {{A new computational tool for establishing model parameter identifiability}},
  journal = {Journal of Computational Biology},
  year = {2009},
  volume = {16},
  number = {6},
  pages = {875-885}
}
Roberts, M. A., August, E., Hamadeh, A., Maini, P. K., McSharry, P. E., Armitage, J. P. & Papachristodoulou, A. A model invalidation-based approach for elucidating biological signalling pathways, applied to the chemotaxis pathway in R. sphaeroides 2009 BMC Systems Biology   article URL  
Abstract: Background:
Developing methods for understanding the connectivity of signalling pathways is a
major challenge in biological research. For this purpose, mathematical models are routinely
developed based on experimental observations, which also allow the prediction of the system
behaviour under different experimental conditions. Often, however, the same experimental data
can be represented by several competing network models.
Results:
In this paper, we developed a novel mathematical model/experiment design cycle to help
determine the probable network connectivity by iteratively invalidating models corresponding to
competing signalling pathways. To do this, we systematically design experiments in silico that
discriminate best between models of the competing signalling pathways. The method determines
the inputs and parameter perturbations that will differentiate best between model outputs,
corresponding to what can be measured/observed experimentally. We applied our method to the
unknown connectivities in the chemotaxis pathway of the bacterium Rhodobacter sphaeroides. We
first developed several models of R. sphaeroides chemotaxis corresponding to different signalling
networks, all of which are biologically plausible. Parameters in these models were fitted so that they
all represented wild type data equally well. The models were then compared to current mutant
data and some were invalidated. To discriminate between the remaining models we used ideas from
control systems theory to determine efficiently in silico an input profile that would result in the
biggest difference in model outputs. However, when we applied this input to the models, we found
it to be insufficient for discrimination in silico. Thus, to achieve better discrimination, we
determined the best change in initial conditions (total protein concentrations) as well as the best
change in the input profile. The designed experiments were then performed on live cells and the
resulting data used to invalidate all but one of the remaining candidate models.
Conclusion:
We successfully applied our method to chemotaxis in R. sphaeroides and the results
from the experiments designed using this methodology allowed us to invalidate all but one of the
proposed network models. The methodology we present is general and can be applied to a range of
other biological networks.
BibTeX:
@article{AugustBMC2009,
  author = {Mark AJ Roberts and Elias August and Abdullah Hamadeh and Philip K Maini and Patrick E McSharry and Judith P Armitage and Antonis Papachristodoulou},
  title = {A model invalidation-based approach for elucidating biological signalling pathways, applied to the chemotaxis pathway in R. sphaeroides},
  journal = {BMC Systems Biology},
  year = {2009},
  volume = {3},
  pages = {105},
  url = {http://www.biomedcentral.com/1752-0509/3/105}
}
August, E. Parameter Identifiability and Optimal Experimental Design 2009 International Conference on Computational Science and Engineering, 2009. CSE '09   inproceedings DOI URL  
Abstract: Nonlinear dynamical systems are prevalent in systems biology, where they are often used to represent a biological system. This paper deals with the problem of finding experimental setups that are as "cheap" as possible (with respect to some measure) and, at the same time, will allow to identify all the unknown parameters of a nonlinear dynamical system. This is important as often identifiability is assumed -- that is, that parameters can be deduced from output data (experimental observations) -- and might lead to extensive, repetitive experiments based only on intuition. We present a novel computational approach that provides a minimal set of required observable outputs in order to obtain full parameter identifiability. In other words, we optimise our experimental setup such that we require the observation of only a few outputs while guaranteeing full parameter identifiability. Furthermore, if the observable output function is given then we provide a computational approach to obtain a minimal set of inputs to the system that will provide full parameter identifiability (if such a set exists). Finally, examples from biology are used to further motivate and illustrate our method.
BibTeX:
@inproceedings{AugustCSE2009,
  author = {August, E.},
  title = {Parameter Identifiability and Optimal Experimental Design},
  booktitle = {International Conference on Computational Science and Engineering, 2009. CSE '09},
  year = {2009},
  pages = {277 - 284},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5283106&tag=1},
  doi = {10.1109/CSE.2009.39}
}
Brodersen, K. H. Decoding mental activity from neuroimaging data---the science behind mind-reading 2009 The New Collection, Oxford   article  
BibTeX:
@article{brodersen_decoding_2009,
  author = {Kay H. Brodersen},
  title = {Decoding mental activity from neuroimaging data---the science behind mind-reading},
  journal = {The New Collection, Oxford},
  year = {2009},
  volume = {4},
  pages = {50--61}
}
Busetto, A. G. & Buhmann, J. M. Structure Identification by Optimized Interventions 2009 Proceedings of the 12th International Conference on Artificial Intelligence and Statistics   inproceedings PDF  
Abstract: We consider the problem of optimal experimental design in structure identification. Whereas standard approaches simply minimize Shannon’s entropy of the estimated parameter posterior, we show how to select between alternative model configurations, too. Our method specifies the intervention that makes an experiment capable of determining whether or not a particular configuration hypothesis is correct. This is performed by a novel clustering technique in approximated Bayesian parameter estimation for non-linear dynamical systems. The computation of the perturbation that minimizes the effective number of clusters in the belief state is constrained by the increase of the expected Kullback-Leibler divergence between the parameter prior and the posterior. This enables the disambiguation of persisting alternative explanations in cases where standard design systematically fails. Its applicability is illustrated with a biochemical Goodwin model, showing correct identification between multiple kinetic structures. We expect that our approach will prove useful especially for complex structures with reduced observability and multimodal posteriors.
BibTeX:
@inproceedings{busetto09aistats,
  author = {A. G. Busetto and J. M. Buhmann},
  title = {Structure Identification by Optimized Interventions},
  booktitle = {Proceedings of the 12th International Conference on Artificial Intelligence and Statistics},
  year = {2009},
  pages = {57--64}
}
Busetto, A. G. & Buhmann, J. M. Stable Bayesian Parameter Estimation for Biological Dynamical Systems 2009 Proceedings of the 12th IEEE International Conference on Computational Science and Engineering   inproceedings URL  
BibTeX:
@inproceedings{busetto09cse,
  author = {A. G. Busetto and J. M. Buhmann},
  title = {Stable Bayesian Parameter Estimation for Biological Dynamical Systems},
  booktitle = {Proceedings of the 12th IEEE International Conference on Computational Science and Engineering},
  year = {2009},
  pages = {???},
  url = {http://portal.acm.org/citation.cfm?id=1632707.1633262&coll=GUIDE&dl=GUIDE&CFID=67693965&CFTOKEN=38037981}
}
Busetto, A. G., Ong, C. S. & Buhmann, J. M. Optimized Expected Information Gain for Nonlinear Dynamical Systems 2009 Proceedings of the International Conference on Machine Learning   inproceedings PDF  
Abstract: This paper addresses the problem of active model selection for nonlinear dynamical systems. We propose a novel learning approach that selects the most informative subset of time-dependent variables for the purpose of Bayesian model inference. The model selection criterion maximizes the expected Kullback-Leibler divergence between the prior and the posterior probabilities over the models. The proposed strategy generalizes the standard D-optimal design, which is obtained from a uniform prior with Gaussian noise. In addition, our approach allows us to determine an information halting criterion for model identification. We illustrate the benefits of our approach by differentiating between 18 published biochemical models of the TOR signaling pathway, a model selection problem in systems biology. By generating pivotal selection experiments, our strategy outperforms the standard Aoptimal, D-optimal and E-optimal sequential design techniques.
BibTeX:
@inproceedings{busetto09opteig,
  author = {Alberto Giovanni Busetto and Cheng Soon Ong and Joachim M. Buhmann},
  title = {Optimized Expected Information Gain for Nonlinear Dynamical Systems},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  year = {2009},
  pages = {97--104}
}
Claassen, M., Aebersold, R. & Buhmann, J. M. Proteome coverage prediction with infinite Markov models. 2009 Bioinformatics   article URL  
Abstract: MOTIVATION: Liquid chromatography tandem mass spectrometry (LC-MS/MS) is the predominant method to comprehensively characterize complex protein mixtures such as samples from prefractionated or complete proteomes. In order to maximize proteome coverage for the studied sample, i.e. identify as many traceable proteins as possible, LC-MS/MS experiments are typically repeated extensively and the results combined. Proteome coverage prediction is the task of estimating the number of peptide discoveries of future LC-MS/MS experiments. Proteome coverage prediction is important to enhance the design of efficient proteomics studies. To date, there does not exist any method to reliably estimate the increase of proteome coverage at an early stage. RESULTS: We propose an extended infinite Markov model DiriSim to extrapolate the progression of proteome coverage based on a small number of already performed LC-MS/MS experiments. The method explicitly accounts for the uncertainty of peptide identifications. We tested DiriSim on a set of 37 LC-MS/MS experiments of a complete proteome sample and demonstrated that DiriSim correctly predicts the coverage progression already from a small subset of experiments. The predicted progression enabled us to specify maximal coverage for the test sample. We demonstrated that quality requirements on the final proteome map impose an upper bound on the number of useful experiment repetitions and limit the achievable proteome coverage.
BibTeX:
@article{CAB09,
  author = {Claassen, M. and Aebersold, R. and Buhmann, J. M.},
  title = {Proteome coverage prediction with infinite {M}arkov models.},
  journal = {Bioinformatics},
  year = {2009},
  volume = {25},
  number = {12},
  pages = {i154-60},
  url = {http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?cmd=prlinks&dbfrom=pubmed&retmode=ref&id=19477982}
}
August, E. & Papachristodoulou, A. Efficient, Sparse Biological Network Determination 2009 BMC Systems Biology   article  
BibTeX:
@article{EfficientSparse,
  author = {E.~August and A.~Papachristodoulou},
  title = {{Efficient, Sparse Biological Network Determination}},
  journal = {BMC Systems Biology},
  year = {2009},
  volume = {3},
  pages = {25}
}
Floros, X. E., Fuchs, T. J., Rechsteiner, M. P., Spinas, G., Moch, H. & Buhmann, J. M. Graph-Based Pancreatic Islet Segmentation for Early Type 2 Diabetes Mellitus on Histopathological Tissue 2009 MICCAI (1)   inproceedings URL  
BibTeX:
@inproceedings{FlorosMICCAI09,
  author = {Xenofon E. Floros and Thomas J. Fuchs and Markus P. Rechsteiner and Giatgen Spinas and Holger Moch and Joachim M. Buhmann},
  title = {Graph-Based Pancreatic Islet Segmentation for Early Type 2 Diabetes Mellitus on Histopathological Tissue},
  booktitle = {MICCAI (1)},
  year = {2009},
  pages = {633-640},
  url = {http://www.ep.liu.se/ecp/047/012/}
}
Frank, M., Plaue, M. & Hamprecht, F. A. Denoising of Continuous-Wave Time-Of-Flight Depth Images using Confidence Measures 2009 Optical Engineering   article URL PDF  
Abstract: Time-of-flight range sensors with on-chip continuous-wave correlation of radio frequency modulated signals are increasingly popular. They simultaneously deliver depth maps and intensity images with noise and systematic errors that are unique for this particular kind of data. Based on recent theoretical findings on the dominating noise processes we propose specific variants of normalized convolution and median filtering, both adaptive and non-adaptive, to the denoising of the range images. We examine the proposed filters on real-world depth maps with varying reflectivity, structure,over-exposure, and illumination. The best results are obtained by adaptive filters that locally adjust the level of smoothing using the estimated modulation amplitude as a measure of confidence.
BibTeX:
@article{frank.ea:denoising:2009,
  author = {Mario Frank and Matthias Plaue and Fred A. Hamprecht},
  title = {Denoising of Continuous-Wave Time-Of-Flight Depth Images using Confidence Measures},
  journal = {Optical Engineering},
  year = {2009},
  volume = {48},
  number = {7},
  url = {http://dx.doi.org/10.1117/1.3159869}
}
Frank, M., Plaue, M., Rapp, H., Köthe, U., Jähne, B. & Hamprecht, F. A. Theoretical and Experimental Error Analysis of Continuous-Wave Time-Of-Flight Range Cameras 2009 Optical Engineering   article PDF  
BibTeX:
@article{frank09_TOFerror,
  author = {Mario Frank and Matthias Plaue and Holger Rapp and Ullrich K\"othe and Bernd J\"ahne and Fred A. Hamprecht},
  title = {Theoretical and Experimental Error Analysis of Continuous-Wave Time-Of-Flight Range Cameras},
  journal = {Optical Engineering},
  publisher = {Society of Photo-Optical Instrumentation Engineers (SPIE)},
  year = {2009},
  volume = {48},
  number = {1}
}
Dahl, E., En-Nia, A., Wiesmann, F., Krings, R., Djudjaj, S., Breuer, E., Fuchs, T., Wild, P., Hartmann, A., Dunn, S. & Mertens, P. Nuclear detection of Y-box protein-1 (YB-1) closely associates with progesterone receptor negativity and is a strong adverse survival factor in human breast cancer 2009 BMC Cancer   article DOI URL  
BibTeX:
@article{FuchsBMCCancer2009a,
  author = {Edgar Dahl and Abdelaziz En-Nia and Frank Wiesmann and Renate Krings and Sonja Djudjaj and Elisabeth Breuer and Thomas Fuchs and Peter Wild and Arndt Hartmann and Sandra Dunn and Peter Mertens},
  title = {Nuclear detection of Y-box protein-1 (YB-1) closely associates with progesterone receptor negativity and is a strong adverse survival factor in human breast cancer},
  journal = {BMC Cancer},
  year = {2009},
  volume = {9},
  number = {1},
  pages = {410},
  url = {http://www.biomedcentral.com/1471-2407/9/410},
  doi = {10.1186/1471-2407-9-410}
}
Fuchs, T. J., Haybaeck, J., Wild, P. J., Heikenwalder, M., Moch, H., Aguzzi, A. & Buhmann, J. M. Randomized Tree Ensembles for Object Detection in Computational Pathology. 2009 ISVC (1)   inproceedings URL  
BibTeX:
@inproceedings{FuchsISVC2009,
  author = {Thomas J. Fuchs and Johannes Haybaeck and Peter J. Wild and Mathias Heikenwalder and Holger Moch and Adriano Aguzzi and Joachim M. Buhmann},
  title = {Randomized Tree Ensembles for Object Detection in Computational Pathology.},
  booktitle = {ISVC (1)},
  publisher = {Springer},
  year = {2009},
  volume = {5875},
  pages = {367-378},
  url = {http://dblp.uni-trier.de/db/conf/isvc/isvc2009-1.html#FuchsHWHMAB09}
}
Fuchs, T. J. & Buhmann, J. M. Inter-Active Learning of Randomized Tree Ensembles for Object Detection 2009 ICCV Workshop on On-line Learning for Computer Vision, 2009   inproceedings  
BibTeX:
@inproceedings{FuchsOLCV2009,
  author = {Thomas J. Fuchs and Joachim M. Buhmann},
  title = {Inter-Active Learning of Randomized Tree Ensembles for Object Detection},
  booktitle = {ICCV Workshop on On-line Learning for Computer Vision, 2009},
  publisher = {IEEE},
  year = {2009}
}
Frank, M., Streich, A. P., Basin, D. & Buhmann, J. M. A Probabilistic Approach to Hybrid Role Mining 2009 16th ACM Conference on Computer and Communications Security (CCS 2009)   inproceedings PDF  
Abstract: Role mining algorithms address an important access control problem: configuring a role-based access control system. Given a direct assignment of users to permissions, role mining discovers a set of roles together with an assignment of users to roles. The results should closely agree with the direct assignment. Moreover, the roles should be understandable from the business perspective in that they reflect functional roles within the enterprise. This requires hybrid role mining methods that work with both direct assignments and business information from the enterprise. In this paper, we provide statistical measures to analyze the relevance of different kinds of business information for defining roles. We then present an approach that incorporates relevant business information into a probabilistic model with an associated algorithm for hybrid role mining. Experiments on actual enterprise data show that our algorithm yields roles that both explain the given user-permission assignments and are meaningful from the business perspective.

Categories and Subject Descriptors: K.6 [Management of Computing and Information Systems]: Security and Protection
General Terms: Security, Management, Algorithms
Keywords: RBAC, Role Mining, Hybrid Role Mining, Machine
Learning, Business Meaning

BibTeX:
@inproceedings{hybridRM_ccs09,
  author = {Mario Frank and Andreas P. Streich and David Basin and Joachim M. Buhmann},
  title = {A Probabilistic Approach to Hybrid Role Mining},
  booktitle = {16th ACM Conference on Computer and Communications Security (CCS 2009)},
  publisher = {ACM},
  year = {2009}
}
Streich, A. P., Frank, M., Basin, D. & Buhmann, J. M. Multi-Assignment Clustering for Boolean Data 2009 Proceedings of the 26th International Conference on Machine Learning   inproceedings PDF  
Abstract: Multi-Assignment Clustering for Boolean Data

Conventional clustering methods typically assume that each data item belongs to a single cluster. This assumption does not hold in general. In order to overcome this limitation, we propose a generative method for clustering vectorial data, where each object can be assigned to multiple clusters. Using a deterministic annealing scheme, our method decomposes the observed data into the contributions of individual clusters and infers their parameters.
Experiments on synthetic Boolean data show that our method achieves higher accuracy in the source parameter estimation and superior cluster stability compared to state-of-the-art approaches. We also apply our method to an important problem in computer security known as role mining. Experiments on real-world access control data show performance gains in generalization to new employees against other multi-assignment methods. In challenging situations with high noise levels, our approach maintains its good performance, while alternative state-of-the-art techniques lack robustness.

BibTeX:
@inproceedings{icml2009_MAC,
  author = {Andreas P. Streich and Mario Frank and David Basin and Joachim M. Buhmann},
  title = {Multi-Assignment Clustering for Boolean Data},
  booktitle = {Proceedings of the 26th International Conference on Machine Learning},
  publisher = {Omnipress},
  year = {2009},
  pages = {969--976}
}
Moh, Y. & Buhmann, J. Manifold Regularization for Semi-Supervised Sequential Learning 2009 Proceedings of 34th IEEE International Conference on Acoustics, Speech and Signal Processing   inproceedings  
Abstract: The sequential data flux in many time-series applications require that only a small fraction of the data are stored for future processing. Furthermore, labels for these data are possibly sparse and they might show some biases. To support learning under such restrictive constraints, we combine manifold regularization with sequential learning under a semi-supervised learning scenario. The online learning mechanism integrates a regularization based on the data smoothness assumptions. We present a proof-of-concept for illustrative toy problems, and we apply the algorithm to a real-world sparse online classification task for music categories.
BibTeX:
@inproceedings{moh:09,
  author = {Yvonne Moh and Joachim Buhmann},
  title = {Manifold Regularization for Semi-Supervised Sequential Learning},
  booktitle = {Proceedings of 34th IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2009},
  pages = {1617-1620}
}
August, E. Parameter identifiability and optimal experimental design 2009 The 12th IEEE International Conference on Computational Science and Engineering (CSE-09)   inproceedings  
BibTeX:
@inproceedings{Parameterid,
  author = {E.~August},
  title = {{Parameter identifiability and optimal experimental design}},
  booktitle = {The 12th IEEE International Conference on Computational Science and Engineering (CSE-09)},
  year = {2009}
}
Pletscher, P., Ong, C. S. & Buhmann, J. M. Spanning Tree Approximations for Conditional Random Fields 2009 Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS) 2009   inproceedings  
Abstract: In this work we show that one can train Conditional Random Fields of intractable graphs effectively and efficiently by considering a mixture of random spanning trees of the underlying graphical model. Furthermore, we show how a maximum-likelihood estimator of such a training objective can subsequently be used for prediction on the full graph. We present experimental results which improve on the state-of-the-art. Additionally, the training objective is less sensitive to the regularization than pseudo-likelihood based training approaches. We perform the experimental validation on two classes of data sets where structure is important: image denoising and multilabel classi cation.
BibTeX:
@inproceedings{Pletscher:SpanningCRF:2009,
  author = {Pletscher, Patrick and Ong, Cheng Soon and Buhmann, Joachim M.},
  title = {Spanning Tree Approximations for Conditional Random Fields},
  booktitle = {Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics ({AISTATS}) 2009},
  publisher = {JMLR: W\&CP 5},
  year = {2009},
  pages = {408--415}
}
Raman, S., Fuchs, T. J., Wild, P. J., Dahl, E. & Roth, V. The Bayesian group-Lasso for analyzing contingency tables 2009 ICML   inproceedings  
BibTeX:
@inproceedings{Raman2009,
  author = {Sudhir Raman and Thomas J. Fuchs and Peter J. Wild and Edgar Dahl and Volker Roth},
  title = {The Bayesian group-Lasso for analyzing contingency tables},
  booktitle = {ICML},
  year = {2009},
  pages = {111}
}
Reiter, L., Claassen, M., Schrimpf, S. P., Jovanovic, M., Schmidt, A., Buhmann, J. M., Hengartner, M. O. & Aebersold, R. Protein Identification False Discovery Rates for Very Large Proteomics Data Sets Generated by Tandem Mass Spectrometry 2009 Mol Cell Proteomics   article DOI URL  
Abstract: Comprehensive characterization of a proteome is a fundamental goal in proteomics. To achieve saturation coverage of a proteome or specific subproteome via tandem mass spectrometric identification of tryptic protein sample digests, proteomics data sets are growing dramatically in size and heterogeneity. The trend toward very large integrated data sets poses so far unsolved challenges to control the uncertainty of protein identifications going beyond well established confidence measures for peptide-spectrum matches. We present MAYU, a novel strategy that reliably estimates false discovery rates for protein identifications in large scale data sets. We validated and applied MAYU using various large proteomics data sets. The data show that the size of the data set has an important and previously underestimated impact on the reliability of protein identifications. We particularly found that protein false discovery rates are significantly elevated compared with those of peptide-spectrum matches. The function provided by MAYU is critical to control the quality of proteome data repositories and thereby to enhance any study relying on these data sources. The MAYU software is available as standalone software and also integrated into the Trans-Proteomic Pipeline.
BibTeX:
@article{RCBHA09,
  author = {Reiter, Lukas and Claassen, Manfred and Schrimpf, Sabine P. and Jovanovic, Marko and Schmidt, Alexander and Buhmann, Joachim M. and Hengartner, Michael O. and Aebersold, Ruedi},
  title = {{Protein Identification False Discovery Rates for Very Large Proteomics Data Sets Generated by Tandem Mass Spectrometry}},
  journal = {Mol Cell Proteomics},
  year = {2009},
  volume = {8},
  number = {11},
  pages = {2405-2417},
  url = {http://www.mcponline.org/cgi/content/abstract/8/11/2405},
  doi = {10.1074/mcp.M900317-MCP200}
}
Saur, S. C., Alkadhi, H., Stolzmann, P., Baumüller, S., Leschka, S., Scheffel, H., Desbiolles, L., Fuchs, T. J., Szekely, G. & Cattin, P. C. Effect of Reader Experience on Variability and Evaluation Time of Coronary Plaque Detection with Computed Tomography Coronary Angiography 2009 European Radiology   article  
BibTeX:
@article{Saur2009a,
  author = {Stefan C. Saur and Hatem Alkadhi and Paul Stolzmann and Stephan Baum{\"u}ller and Sebastian Leschka and Hans Scheffel and Lotus Desbiolles and Thomas J. Fuchs and Gabor Szekely and Philippe C. Cattin},
  title = {Effect of Reader Experience on Variability and Evaluation Time of Coronary Plaque Detection with Computed Tomography Coronary Angiography},
  journal = {European Radiology},
  year = {2009}
}
Saur, S. C., Cattin, P. C., Desbiolles, L., Fuchs, T. J., Szekely, G. & Alkadhi, H. Prediction rules for the detection of coronary artery plaques: evidence from cardiac CT 2009 Investigative Radiology   article URL  
BibTeX:
@article{Saur2009b,
  author = {Stefan C Saur and Philippe C Cattin and Lotus Desbiolles and Thomas J Fuchs and Gabor Szekely and Hatem Alkadhi},
  title = {Prediction rules for the detection of coronary artery plaques: evidence from cardiac CT},
  journal = {Investigative Radiology},
  year = {2009},
  volume = {44},
  number = {8},
  pages = {483-490},
  url = {http://dx.doi.org/10.1097/RLI.0b013e3181a8afc4}
}
Saur, S. C., Alkadhi, H., Desbiolles, L., Fuchs, T. J., Szekely, G. & Cattin, P. C. Guided review by frequent itemset mining: additional evidence for plaque detection 2009 International Journal of Computer Assisted Radiology and Surgery   article URL  
Abstract: A guided review process to support manual coronary plaque detection in computed tomography coronary angiography (CTCA) data sets is proposed. The method learns the spatial plaque distribution patterns by using the frequent itemset mining algorithm and uses this knowledge to predict potentially missed plaques during detection.
BibTeX:
@article{Saur2009c,
  author = {Stefan C. Saur and Hatem Alkadhi and Lotus Desbiolles and Thomas J. Fuchs and Gabor Szekely and Philippe C. Cattin},
  title = {Guided review by frequent itemset mining: additional evidence for plaque detection},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2009},
  volume = {4},
  number = {3},
  pages = {263--271},
  url = {http://dx.doi.org/10.1007/s11548-009-0290-5}
}
Schmidt, A., Claassen, M. & Aebersold, R. Directed mass spectrometry: towards hypothesis-driven proteomics 2009 Current Opinion in Chemical Biology   article  
BibTeX:
@article{schmidt2009directed,
  author = {Schmidt, A. and Claassen, M. and Aebersold, R.},
  title = {{Directed mass spectrometry: towards hypothesis-driven proteomics}},
  journal = {Current Opinion in Chemical Biology},
  publisher = {Elsevier},
  year = {2009}
}
Schweikert, G., Zien, A., Zeller, G., Behr, J., Dieterich, C., Ong, C. S., Philips, P., Bona, F. D., Hartmann, L., Bohlen, A., Krer, N., Sonnenburg, S. & Rsch, G. mGene: Accurate SVM-Based Gene Finding with an Application to Nematode Genomes 2009 Genome Research   article  
BibTeX:
@article{schweikert09mgeasg,
  author = {Gabriele Schweikert and Alexander Zien and Georg Zeller and Jonas Behr and Christoph Dieterich and Cheng Soon Ong and Petra Philips and Fabio De Bona and Lisa Hartmann and Anja Bohlen and Nina Kr\"ger and S\"oren Sonnenburg, and Gunnar R\"tsch},
  title = {mGene: Accurate SVM-Based Gene Finding with an Application to Nematode Genomes},
  journal = {Genome Research},
  year = {2009},
  note = {Advance access on 29 June 2009}
}
Schweikert, G., Behr, J., Zien, A., Zeller, G., Ong, C. S., Sonnenburg, S. & Rätsch, G. mGene.web: a web service for accurate computational gene finding 2009 Nucleic Acids Research   article  
BibTeX:
@article{schweikert09mgewsa,
  author = {Gabriele Schweikert and Jonas Behr and Alexander Zien and Georg Zeller and Cheng Soon Ong and S\"oren Sonnenburg and Gunnar R\"atsch},
  title = {mGene.web: a web service for accurate computational gene finding},
  journal = {Nucleic Acids Research},
  year = {2009},
  volume = {37},
  note = {Web Server Issue}
}
Stephan, K. E., Kasper, L., Brodersen, KH. & Mathys, C. Functional and Effective Connectivity 2009 Klinische Neurophysiologie   article DOI URL  
Abstract: Neurophysiological and imaging procedures to measure brain activity, such as fMRI or EEG, are employed in neuroscience to investigate processes of functional specialisation and functional integration in the human brain. Functioal integration can be described in two distinct ways: functional connectivity and eff ective connectivity. Whereas functional connectivity merely describes the statistical dependence between two time series, the concept of eff ective connectivity requires a mechanistic model of the causative effects upon which the data to be observed are based. This article summarises the conceptual and methodological principles of modern techniques for the analysis of functional and effective connectivity on the basis of fMRI and electrophysiological data. Particular emphasis is placed on dynamic causal modelling (DCM), a new procedure for the analysis of nonlinear neuronal systems. This method has a highly promising potential for clinical applications, e.g., for decoding pathological mechanisms in brain diseases and for the establishment of neurologically valid diagnostic classifications.
BibTeX:
@article{stephan_functional_2009,
  author = {K E Stephan and L Kasper and {KH} Brodersen and C Mathys},
  title = {Functional and Effective Connectivity},
  journal = {Klinische Neurophysiologie},
  year = {2009},
  volume = {40},
  pages = {222--232},
  url = {http://dx.doi.org/10.1055/S-0029-1243196},
  doi = {10.1055/S-0029-1243196}
}
Streich, A. P. & Buhmann, J. M. Ignoring Co-Occurring Sources in Learning from Multi-Labeled Data Leads to Model Mismatch 2009 MLD09: ECML/PKDD 2009 Workshop on Learning from Multi-Label Data   inproceedings  
Abstract: The task of multi-label classification is of growing interest in many applications of machine learning. Most currently employed techniques reduce the problem to a series of independent single-label classification problems, thus ignoring the information a data item contains about the other classes it belongs to. Taking a generative viewpoint, we interpret a multi-labeled data item as a combination of independent emissions of all sources it belongs to. We show that if the combination function is a bijection in a single source emission, training an
independent generative classifier by maximum likelihood for every class implies a model mismatch.
BibTeX:
@inproceedings{streich.buhmann:mismatch,
  author = {Andreas P. Streich and Joachim M. Buhmann},
  title = {Ignoring Co-Occurring Sources in Learning from Multi-Labeled Data Leads to Model Mismatch},
  booktitle = {MLD09: ECML/PKDD 2009 Workshop on Learning from Multi-Label Data},
  year = {2009}
}
Wild, P. J., Fuchs, T. J., Stoehr, R., Zimmermann, D., Frigerio, S., Padberg, B., Steiner, I., Zwarthoff, E. C., Burger, M., Denzinger, S., Hofstaedter, F., Kristiansen, G., Hermanns, T., Seifert, H.-H., Provenzano, M., Sulser, T., Roth, V., Buhmann, J. M., Moch, H. & Hartmann, A. Detection of Urothelial Bladder Cancer Cells in Voided Urine Can Be Improved by a Combination of Cytology and Standardized Microsatellite Analysis 2009 Cancer Epidemiol Biomarkers Prev   article DOI URL  
BibTeX:
@article{WildFuchs2009,
  author = {Peter J. Wild and Thomas J. Fuchs and Robert Stoehr and Dieter Zimmermann and Simona Frigerio and Barbara Padberg and Inbal Steiner and Ellen C. Zwarthoff and Maximilian Burger and Stefan Denzinger and Ferdinand Hofstaedter and Glen Kristiansen and Thomas Hermanns and Hans-Helge Seifert and Maurizio Provenzano and Tullio Sulser and Volker Roth and Joachim M. Buhmann and Holger Moch and Arndt Hartmann},
  title = {{Detection of Urothelial Bladder Cancer Cells in Voided Urine Can Be Improved by a Combination of Cytology and Standardized Microsatellite Analysis}},
  journal = {Cancer Epidemiol Biomarkers Prev},
  year = {2009},
  volume = {18},
  number = {6},
  pages = {1798-1806},
  url = {http://cebp.aacrjournals.org/cgi/content/abstract/18/6/1798},
  doi = {10.1158/1055-9965.EPI-09-0099}
}
Brand, M. & Pletscher, P. A conditional random field for automatic photo editing 2008 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   article  
BibTeX:
@article{BrandP:CRFAutomaticPhotoEditing:2008,
  author = {Matthew Brand and Patrick Pletscher},
  title = {A conditional random field for automatic photo editing},
  booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})},
  year = {2008}
}
Cerf, M., Harel, J., Einhäuser, W. & Koch, C. Predicting human gaze using low-level saliency combined with face detection 2008 Advances in Neural Information Processing Systems (NIPS) 20   inproceedings URL  
Abstract: Under natural viewing conditions, human observers shift their gaze to allocate
processing resources to subsets of the visual input. Many computational models
try to predict such voluntary eye and attentional shifts. Although the important
role of high level stimulus properties (e.g., semantic information) in search
stands undisputed, most models are based on low-level image properties. We here
demonstrate that a combined model of face detection and low-level saliency significantly
outperforms a low-level model in predicting locations humans fixate on,
based on eye-movement recordings of humans observing photographs of natural
scenes, most of which contained at least one person. Observers, even when not instructed
to look for anything particular, fixate on a face with a probability of over
80% within their first two fixations; furthermore, they exhibit more similar scanpaths
when faces are present. Remarkably, our model’s predictive performance in
images that do not contain faces is not impaired, and is even improved in some
cases by spurious face detector responses.
BibTeX:
@inproceedings{Cerf2008,
  author = {Moran Cerf and Jonathan Harel and Wolfgang Einh\"auser and Christof Koch},
  title = {Predicting human gaze using low-level saliency combined with face detection},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 20},
  publisher = {MIT Press},
  year = {2008},
  note = {(accepted)},
  url = {http://books.nips.cc/papers/files/nips20/NIPS2007_1074.pdf}
}
Sigg, C. D. & Buhmann, J. M. Expectation-Maximization for Sparse and Non-Negative PCA 2008 Proc. 25th International Conference on Machine Learning,   inproceedings PDF  
BibTeX:
@inproceedings{chrsigg2008a,
  author = {Christian D. Sigg and Joachim M. Buhmann},
  title = {Expectation-Maximization for Sparse and Non-Negative PCA},
  booktitle = {Proc. 25th International Conference on Machine Learning,},
  year = {2008}
}
Einhäuser, W., Stout, J., Koch, C. & Carter, O. Pupil dilation reflects perceptual selection and predicts subsequent stability in perceptual rivalry 2008 Proceedings of the National Academy of Sciences of the United States of America   article URL  
Abstract: During sustained viewing of an ambiguous stimulus, an individual’s perceptual experience will generally switch between the different possible alternatives rather than stay fixed on one interpretation (perceptual rivalry). Here, we measured pupil diameter while subjects viewed different ambiguous visual and auditory stimuli. For all stimuli tested, pupil diameter increased just before the reported perceptual switch and the relative amount of dilation before this switch was a significant predictor of the subsequent duration of perceptual stability. These results could not be explained by blink or eye-movement effects, the motor response or stimulus driven changes in retinal input. Because pupil dilation reflects levels of norepinephrine (NE) released from the locus coeruleus (LC), we interpret these results as suggestive that the LC–NE complex may play the same role in perceptual selection as in behavioral decision making.
BibTeX:
@article{einhauser.stout.ea:pupil,
  author = {Wolfgang Einh\"auser and James Stout and Christof Koch and Olivia Carter},
  title = {Pupil dilation reflects perceptual selection and predicts subsequent stability in perceptual rivalry},
  journal = {Proceedings of the National Academy of Sciences of the United States of America},
  year = {2008},
  volume = {105},
  number = {5},
  pages = {1704-1709},
  url = {http://www.pnas.org/cgi/doi/10.1073/pnas.0707727105}
}
Einhäuser, W., Rutishauser, U. & Koch, C. Task-demands can immediately reverse the effects of sensory-driven saliency in complex visual stimuli 2008 Journal of Vision   article  
Abstract: In natural vision both stimulus features and task demands affect an observer’s attention. However, the relationship between sensory-driven (“bottom-up”) and task-dependent (“top-down”) factors remains controversial: Can task-demands counteract strong sensory signals fully, quickly and irrespective of bottom-up features? To measure attention under naturalistic conditions, we recorded eye-movements in human observers, while they viewed photographs of outdoor scenes. In the first experiment, smooth modulations of contrast biased the stimuli’s sensory-driven saliency towards one side. In free-viewing, observers’ eye-positions were immediately biased toward the high-contrast, i.e. high saliency, side. However, this sensory-driven bias disappeared entirely when observers searched for a bull’s eye target embedded with equal probability to either side of the stimulus. When the target always occurred in the low-contrast side, observers’ eye-positions were immediately biased towards this low-saliency side, i.e. the sensory-driven bias reversed. Hence task-demands do not only override sensory-driven saliency, but also actively countermand it. In a second experiment, a 5-Hz flicker replaced the contrast-gradient. Whereas the bias was less persistent in free viewing, the overriding and reversal took longer to deploy. Hence, insufficient sensory-driven saliency cannot account for the bias reversal. In a third experiment, subjects searched for a spot of locally increased contrast (“oddity”) instead of the bull’s eye (“template”). In contrast to the other conditions, a slight sensory-driven free-viewing bias prevails in this condition. In a forth experiment we demonstrate that at known locations template targets are detected faster than oddity targets, suggesting that the former induce a stronger top-down drive when used as search targets. Taken together, task demands can override sensory-driven saliency in complex visual stimuli almost immediately, and the extent of overriding depends on the search target and the overridden feature, but not on the latter’s free-viewing saliency.
BibTeX:
@article{Einhauser2008,
  author = {W Einh{\"a}user and U Rutishauser and C Koch},
  title = {Task-demands can immediately reverse the effects of sensory-driven saliency in complex visual stimuli},
  journal = {Journal of Vision},
  year = {2008},
  note = {in press}
}
Frank, M., Basin, D. & Buhmann, J. M. A Class of Probabilistic Models for Role Engineering 2008 15th ACM Conference on Computer and Communications Security (CCS 2008)   inproceedings PDF  
BibTeX:
@inproceedings{frank.ea:class:2008,
  author = {Mario Frank and David Basin and Joachim M. Buhmann},
  title = {A Class of Probabilistic Models for Role Engineering},
  booktitle = {15th ACM Conference on Computer and Communications Security (CCS 2008)},
  publisher = {ACM},
  year = {2008}
}
Fuchs, T. J., Lange, T., Wild, P. J., Moch, H. & Buhmann, J. M. Weakly Supervised Cell Nuclei Detection and Segmentation on Tissue Microarrays of Renal Cell Carcinoma 2008 Pattern Recognition. DAGM 2008   inproceedings DOI  
BibTeX:
@inproceedings{FuchsDAGM2008,
  author = {Thomas J. Fuchs and Tilman Lange and Peter J. Wild and Holger Moch and Joachim M. Buhmann},
  title = {Weakly Supervised Cell Nuclei Detection and Segmentation on Tissue Microarrays of Renal Cell Carcinoma},
  booktitle = {Pattern Recognition. DAGM 2008},
  publisher = {Springer Berlin / Heidelberg},
  year = {2008},
  volume = {5096},
  pages = {173--182},
  doi = {10.1007/978-3-540-69321-}
}
Fuchs, T. J., Wild, P. J., Moch, H. & Buhmann, J. M. Computational Pathology Analysis of Tissue Microarrays Predicts Survival of Renal Clear Cell Carcinoma Patients 2008 Medical Image Computing and Computer-Assisted Intervention. MICCAI 2008   inproceedings DOI  
BibTeX:
@inproceedings{FuchsMICCAI2008,
  author = {Thomas J. Fuchs and Peter J. Wild and Holger Moch and Joachim M. Buhmann},
  title = {Computational Pathology Analysis of Tissue Microarrays Predicts Survival of Renal Clear Cell Carcinoma Patients},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention. MICCAI 2008},
  publisher = {Springer Berlin / Heidelberg},
  year = {2008},
  volume = {5242},
  pages = {1--8},
  doi = {10.1007/978-3-540-85990-1}
}
Fürnstahl, P., Fuchs, T. J., Schweizer, A., Nagy, L., Székely, G. & Harders, M. Automatic and Robust Forearm Segmentation using Graph Cuts 2008 5th IEEE International Symposium on Biomedical Imaging. ISBI 2008   inproceedings DOI  
BibTeX:
@inproceedings{FurnstahlISBI2008,
  author = {Philipp F\"urnstahl and Thomas J. Fuchs and Andreas Schweizer and Ladislav Nagy and G\'abor Sz\'ekely and Matthias Harders},
  title = {Automatic and Robust Forearm Segmentation using Graph Cuts},
  booktitle = {5th IEEE International Symposium on Biomedical Imaging. ISBI 2008},
  publisher = {IEEE},
  year = {2008},
  pages = {77--80},
  doi = {10.1109/ISBI.2008.4540936}
}
Gluz, O., Wild, P., Meiler, R., Diallo-Danebrock, R., Ting, E., Mohrmann, S., Schuett, G., Dahl, E., Fuchs, T., Herr, A., Gaumann, A., Frick, M., Poremba, C., Nitz, U. & Hartmann, A. Nuclear Karyopherin a2 expression predicts poor survival in patients with advanced breast cancer irrespective of treatment intensity. 2008 International Journal of Cancer   article DOI  
BibTeX:
@article{GlutzIJC2008,
  author = {O. Gluz and P.J. Wild and R. Meiler and R. Diallo-Danebrock and E. Ting and S. Mohrmann and G. Schuett and E. Dahl and T.J. Fuchs and A. Herr and A. Gaumann and M. Frick and C. Poremba and U.A. Nitz and A. Hartmann},
  title = {Nuclear Karyopherin a2 expression predicts poor survival in patients with advanced breast cancer irrespective of treatment intensity.},
  journal = {International Journal of Cancer},
  publisher = {Wiley-Liss, Inc.},
  year = {2008},
  volume = {123/6},
  number = {IF 4,693},
  pages = {1433--1438},
  doi = {10.1002/ijc.23628}
}
Kaynig, V., Fischer, B. & Buhmann, J. M. Probabilistic Image Registration and Anomaly Detection by Nonlinear Warping 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)   inproceedings  
BibTeX:
@inproceedings{kaynig:08,
  author = {Verena Kaynig and Bernd Fischer and Joachim M. Buhmann},
  title = {Probabilistic Image Registration and Anomaly Detection by Nonlinear Warping},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2008},
  pages = {1-8}
}
Moh, Y., Orbanz, P. & Buhmann, J. M. Music Preference Learning with Partial Information 2008 Proccedings of International Conference on Acoustic, Speech, and Signal Processing   inproceedings  
BibTeX:
@inproceedings{Moh2008,
  author = {Y. Moh and P. Orbanz and J. M. Buhmann},
  title = {Music Preference Learning with Partial Information},
  booktitle = {Proccedings of International Conference on Acoustic, Speech, and Signal Processing},
  year = {2008}
}
Moh, Y., Einhäuser, W. & Buhmann, J. Automatic Detection of Learnability under Unreliable and Sparse User Feedback 2008 Pattern Recognition--DAGM 2008   inproceedings PDF  
BibTeX:
@inproceedings{Moh2008a,
  author = {Yvonne Moh and Wolfgang Einh\"auser and Joachim Buhmann},
  title = {Automatic Detection of Learnability under Unreliable and Sparse User Feedback},
  booktitle = {Pattern Recognition--DAGM 2008},
  publisher = {Springer},
  year = {2008}
}
Moh, Y. & Buhmann, J. Kernel Expansion for Online Preference Tracking 2008 9th International Conference on Music Information Retrieval   inproceedings  
BibTeX:
@inproceedings{Moh2008b,
  author = {Yvonne Moh and Joachim Buhmann},
  title = {Kernel Expansion for Online Preference Tracking},
  booktitle = {9th International Conference on Music Information Retrieval},
  year = {2008}
}
Niesen, U. H., Pellet, J. P. & Elisseeff, A. Explanation Trees for Causal Bayesian Networks 2008 Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence   inproceedings PDF  
BibTeX:
@inproceedings{nielsen08uai,
  author = {Ulf Holm Niesen and Jean Philippe Pellet and Andr¥'{e} Elisseeff},
  title = {Explanation Trees for Causal {B}ayesian Networks},
  booktitle = {Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence},
  publisher = {AUAI Press},
  year = {2008},
  pages = {427--434}
}
Asa Ben-Hur, Cheng Soon Ong, Sö. S. B. S. & Rätsch, G. Support vector machines and kernels for computational biology 2008 PLoS Computational Biology   article URL  
BibTeX:
@article{Ong2008,
  author = {Asa Ben-Hur, Cheng Soon Ong, S{\"o}ren Sonnenburg, Bernhard Sch{\"o}lkopf, and Gunnar R{\"a}tsch},
  title = {Support vector machines and kernels for computational biology},
  journal = {PLoS Computational Biology},
  year = {2008},
  volume = {4 (10)},
  number = {10},
  pages = {e1000173},
  url = {http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1000173}
}
Orbanz, P. & Buhmann, J. M. Nonparametric Bayesian Image Segmentation 2008 International Journal of Computer Vision   article  
BibTeX:
@article{orbanz.buhmann:nonparametric,
  author = {P. Orbanz and J.~M. Buhmann},
  title = {Nonparametric {B}ayesian Image Segmentation},
  journal = {International Journal of Computer Vision},
  year = {2008},
  volume = {77}
}
Pellet, J. P. & Elisseeff, A. Using Markov blankets for Causal Structure Learning 2008 Journal of Machine Learning Research   article PDF  
Abstract: We show how a generic feature-selection algorithm returning strongly relevant variables can be turned into a causal structure-learning algorithm. We prove this under the Faithfulness assumption for the data distribution. In a causal graph, the strongly relevant variables for a node X are its parents, children, and children’s parents (or spouses), also known as the Markov blanket of X. Identifying the spouses leads to the detection of the V-structure patterns and thus to causal orientations. Repeating the task for all variables yields a valid partially oriented causal graph. We ?rst show an ef?cient way to identify the spouse links. We then perform several experiments in the continuous domain using the Recursive Feature Elimination feature-selection algorithm with Support Vector Regression and empirically verify the intuition of this direct (but computationally expensive) approach. Within the same framework, we then devise a fast and consistent algorithm, Total Conditioning (TC), and a variant, TCbw, with an explicit backward feature-selection heuristics, for Gaussian data. After running a series of comparative experiments on ?ve arti?cial networks, we argue that Markov blanket algorithms such as TC/TCbw or Grow-Shrink scale better than the reference PC algorithm and provides higher structural accuracy.
BibTeX:
@article{pellet08jmlr,
  author = {Jean Philippe Pellet and Andr\'{e} Elisseeff},
  title = {Using {M}arkov blankets for Causal Structure Learning},
  journal = {Journal of Machine Learning Research},
  year = {2008},
  volume = {9},
  pages = {1295--1342}
}
Pellet, J.-P. & Elisseeff, A. Finding Latent Causes in Causal Networks: an Efficient Approach Based on Markov Blankets 2008 Proceedings of the 22nd Annual Conference on Neural Information Processing Systems   inproceedings  
BibTeX:
@inproceedings{pellet08nips,
  author = {Jean-Philippe Pellet and Andr\'{e} Elisseeff},
  title = {Finding Latent Causes in Causal Networks: an Efficient Approach Based on {M}arkov Blankets},
  booktitle = {Proceedings of the 22nd Annual Conference on Neural Information Processing Systems},
  year = {2008}
}
Streich, A. P. & Buhmann, J. M. Classification of Multi-Labeled Data: A Generative Approach 2008 ECML 2008   inproceedings PDF  
Abstract: Multi-label classification assigns a data item to one or several classes. This problem of multiple labels arises in fields like acoustic and visual scene analysis, news reports and medical diagnosis. In a generative framework, data with multiple labels can be interpreted as additive mixtures of emissions of the individual sources. We propose a deconvolution approach to estimate the individual contributions of each source to a given data item. Similarly, the distributions of multi-label data are computed based on the source distributions. In experiments with synthetic data, the novel approach is compared to existing models and yields more accurate parameter estimates, higher classification accuracy and ameliorated generalization to previously unseen label sets. These improvements are most pronounced on small training data sets. Also on real world acoustic data, the algorithm outperforms other generative models, in particular on small training data sets.
BibTeX:
@inproceedings{streich.buhmann:multilabel_generative,
  author = {Andreas P. Streich and Joachim M. Buhmann},
  title = {Classification of Multi-Labeled Data: A Generative Approach},
  booktitle = {ECML 2008},
  year = {2008},
  note = {(to be published)}
}
Angela Y. J. Yao, Einhäuser, W. Color aids late but not early stages of rapid natural scene recognition 2008 Journal of Vision   article URL  
Abstract: Color has an unresolved role in natural scene recognition. Whereas rapid serial visual presentation paradigms typically find no advantage for colored over grayscale scenes, color seems to play a decisive role for recognition memory. The distinction between detection and memorization has not been addressed directly in one paradigm. Here we asked ten observers to detect animals in 2-s 20 Hz sequences. Each sequence consisted of two 1-s segments, one of grayscale images and one of colored; each segment contained one or no target, totaling zero, one, or two targets per sequence. In one-target sequences, hit rates were virtually the same for targets appearing in the first or second segment, as well as for grayscale and colored targets, though observers were more confident about detecting colored targets. In two-target sequences, observers preferentially reported the second of two identical targets, in comparison to categorically related (same-species animals) or unrelated (different-species animals) targets. Observers also showed a strong preference for reporting colored targets, though only when targets were of different species. Our findings suggest that color has little effect on detection, but is used in later stages of processing. We may speculate that color ensures preferential access to or retrieval from memory when distinct items must be rapidly remembered.
BibTeX:
@article{,
  author = {Angela Y. J. Yao, Einh\"auser, Wolfgang},
  title = {Color aids late but not early stages of rapid natural scene recognition},
  journal = {Journal of Vision},
  year = {2008},
  volume = {8},
  number = {16},
  pages = {1-13},
  note = {article 12},
  url = {http://journalofvision.org/8/16/12/}
}
Steiniger, S., Lange, T., Burghardt, D. & Weibel, R. An Approach for the Classification of Urban Building Structures Based on Discriminant Analysis Techniques 2008 Transactions in GIS   article  
BibTeX:
@article{,
  author = {Stefan Steiniger and Tilman Lange and Dirk Burghardt and Robert Weibel},
  title = {An Approach for the Classification of Urban Building Structures Based on Discriminant Analysis Techniques},
  journal = {Transactions in GIS},
  year = {2008},
  volume = {12(1)},
  pages = {31-59}
}
Busse, L. M., Orbanz, P. & Buhmann, J. M. Cluster Analysis of Heterogeneous Rank Data 2007 Proceedings of the International Conference on Machine Learning   inproceedings  
BibTeX:
@inproceedings{bussel2007,
  author = {Ludwig M. Busse and Peter Orbanz and Joachim M. Buhmann},
  title = {Cluster Analysis of Heterogeneous Rank Data},
  booktitle = {Proceedings of the International Conference on Machine Learning},
  year = {2007},
  pages = {113-120}
}
Cerf, M., Cleary, D. R., Peters, R. J., Einhäuser, W. & Koch, C. Observers are Consistent when Rating Image Conspicuity 2007 Vision Research   article URL PDF  
Abstract: Human perception of an image’s conspicuity depends on the stimulus itself and the observer’s semantic interpretation. We investigated the relative contribution of the former, sensory-driven, component. Participants viewed sequences of images from five different classes—fractals, overhead satellite imagery, grayscale and colored natural scenes, and magazine covers—and graded each numerically according to its perceived conspicuity. We found significant consistency in this rating within and between observers for all image categories. In a subsequent recognition memory test, performance was significantly above chance for all categories, with the weakest memory for satellite imagery, and reaching near ceiling for magazine covers. When repeating the experiment after one year, ratings remained consistent within each observer and category, despite the absence of explicit scene memory. Our findings suggest that the rating of image conspicuity is driven by image-immanent, sensory factors common to all observers.
BibTeX:
@article{Cerf2007,
  author = {Moran Cerf and Daniel R. Cleary and Robert J. Peters and Wolfgang Einh\"auser and Christof Koch},
  title = {Observers are Consistent when Rating Image Conspicuity},
  journal = {Vision Research},
  year = {2007},
  volume = {47},
  number = {24},
  pages = {3052--3060},
  url = {http://dx.doi.org/10.1016/j.visres.2007.06.025}
}
Einhäuser, W., Schumann, F., Bardins, S., Bartl, K., Böning, G., Schneider, E. & König., P. Human eye-head co-ordination in natural exploration 2007 Network: Computation in Neural Systems   article URL PDF  
Abstract: During natural behavior humans continuously adjust their gaze by moving head and eyes,yielding rich dynamics of the retinal input. Sensory coding models, however, typically assumevisual input as smooth or a sequence of static images interleaved by volitional gaze shifts.Are these assumptions valid during free exploration behavior in natural environments? Weused an innovative technique to simultaneously record gaze and head movements in humans,who freely explored various environments (forest, train station, apartment). Most movementsoccur along the cardinal axes, and the predominance of vertical or horizontal movementsdepends on the environment. Eye and head movements co-occur more frequently than theirindividual statistics predicts under an independence assumption. The majority of cooccurringmovements point in opposite directions, consistent with a gaze-stabilizing role ofeye movements. Nevertheless, a substantial fraction of eye movements point in the samedirection as co-occurring head movements. Even under the very most conservativeassumptions, saccadic eye movements alone cannot account for these synergistic movements.Hence nonsaccadic eye movements that interact synergistically with head movements toadjust gaze cannot be neglected in natural visual input. Natural retinal input is continuouslydynamic, and cannot be faithfully modeled as a mere sequence of static frames withinterleaved large saccades.
BibTeX:
@article{Einhauser2007,
  author = {Wolfgang Einh\"auser and Frank Schumann and Stanislavs Bardins and Klaus Bartl and Guido B\"oning and Erich Schneider and Peter K\"onig.},
  title = {Human eye-head co-ordination in natural exploration},
  journal = {Network: Computation in Neural Systems},
  year = {2007},
  volume = {18},
  number = {3},
  pages = {267-297},
  url = {http://www.informaworld.com/openurl?genre=article&issn=0954-898X&volume=18&issue=3&spage=267}
}
Einhäuser, W., Koch, C. & Makeig, S. The duration of the attentional blink in natural scenes depends on stimulus category 2007 Vision Research   article URL PDF  
Abstract: Humans comprehend the ''gist'' of even a complex natural scene within a small fraction of a second. If, however, observers are asked to detect targets in a sequence of rapidly presented items, recognition of a target succeeding another target by about a third of a second is severely impaired, the ''attentional blink'' (AB) [Raymond, J. E., Shapiro, K. L., & Arnell, K. M. (1992). Temporary suppression of visual processing in an RSVP task: an attentional blink? Journal of Experimental Psychology. Human Perception and Performance, 18, 849-860].Since most experiments on the AB use well controlled but artificial stimuli, the question arises whether the same phenomenon occurs for complex, natural stimuli, and if so, whether its specifics depend on stimulus category. Here we presented rapid sequences of complex stimuli (photographs of objects, scenes and faces) and asked observers to detect and remember items of a specific category (either faces, watches, or both). We found a consistent AB for both target categories but the duration of the AB depended on the target category.
BibTeX:
@article{Einhauser2007a,
  author = {Wolfgang Einh\"auser and Christof Koch and Scott Makeig},
  title = {The duration of the attentional blink in natural scenes depends on stimulus category},
  journal = {Vision Research},
  year = {2007},
  volume = {47},
  number = {5},
  pages = {597-607},
  url = {http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6T0W-4MYF60S-6&_user=791130&_coverDate=03/31/2007&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000043379&_version=1&_urlVersion=0&_userid=791130&md5=a7a9c435d306221ebe934dc213738dbf}
}
Einhäuser, W., Mundhenk, T. N., Baldi, P., Koch, C. & Itti, L. A Bottom-Up Model of Spatial Attention Predicts Human Error Patterns in Rapid Scene Recognition 2007 Journal of Vision   article URL PDF  
Abstract: Humans demonstrate a peculiar ability to detect complex targets in rapidly presented natural scenes. Recent studies suggest that (nearly) no focal attention is required for overall performance in such tasks. Little is known, however, of how detection performance varies from trial to trial and which stages in the processing hierarchy limit performance: bottom–up visual processing (attentional selection and/or recognition) or top–down factors (e.g., decision-making, memory, or alertness fluctuations)? To investigate the relative contribution of these factors, eight human observers performed an animal detection task in natural scenes presented at 20 Hz. Trial-by-trial performance was highly consistent across observers, far exceeding the prediction of independent errors. This consistency demonstrates that performance is not primarily limited by idiosyncratic factors but by visual processing. Two statistical stimulus properties, contrast variation in the target image and the information-theoretical measure of “surprise” in adjacent images, predict performance on a trial-by-trial basis. These measures are tightly related to spatial attention, demonstrating that spatial attention and rapid target detection share common mechanisms. To isolate the causal contribution of the surprise measure, eight additional observers performed the animal detection task in sequences that were reordered versions of those all subjects had correctly recognized in the first experiment. Reordering increased surprise before and/or after the target while keeping the target and distractors themselves unchanged. Surprise enhancement impaired target detection in all observers. Consequently, and contrary to several previously published findings, our results demonstrate that attentional limitations, rather than target recognition alone, affect the detection of targets in rapidly presented visual sequences.
BibTeX:
@article{Einhauser2007b,
  author = {Wolfgang Einh\"auser and T. Nathan Mundhenk and Pierre Baldi and Christof Koch and Laurent Itti},
  title = {A Bottom-Up Model of Spatial Attention Predicts Human Error Patterns in Rapid Scene Recognition},
  journal = {Journal of Vision},
  year = {2007},
  volume = {7},
  number = {10},
  pages = {1-13},
  url = {http://www.journalofvision.org/7/10/6/}
}
Fischer, B., Roth, V. & Buhmann, J. Time-Series Alignment by Non-Negative Multiple Generalized Canonical Correlation Analysis 2007 BMC Bioinformatics   article URL  
Abstract: bf Background: Quantitative analysis of differential protein expressions requires to align temporal elution measurements from liquid chromatography coupled to mass spectrometry (LC/MS). We propose multiple Canonical Correlation Analysis (mCCA) as a method to align the non-linearly distorted time scales of repeated LC/MS experiments in a robust way.\ bf Results: Multiple canonical correlation analysis is able to map several time series to a consensus time scale. The alignment function is learned in a supervised fashion. We compare our approach with previously published methods for aligning mass spectrometry data on a large proteomics dataset. The proposed method significantly increases the number of proteins that are identified as being differentially expressed in different biological samples.\ bf Conclusion: Jointly aligning multiple liquid chromatography/mass spectrometry samples by mCCA substantially increases the detection rate of potential bio-markers which significantly improves the interpretability of LC/MS data.
BibTeX:
@article{fischer.roth.ea:time-series,
  author = {Bernd Fischer and Volker Roth and Joachim Buhmann},
  title = {Time-Series Alignment by Non-Negative Multiple Generalized Canonical Correlation Analysis},
  journal = {BMC Bioinformatics},
  year = {2007},
  volume = {8},
  number = {S10},
  pages = {S4},
  url = {http://dx.doi.org/10.1186/1471-2105-8-S10-S4}
}
Fischer, B., Roth, V. & Buhmann, J. M. Time-Series Alignment by Non-Negative Multiple Generalized Canonical Correlation Analysis 2007 Computational Intelligence Methods for Bioinformatics and Biostatistics   inproceedings URL  
Abstract: For a quantitative analysis of differential protein expression, one has to overcome the problem of aligning time series of measurements from liquid chromatography coupled to mass spectrometry. When repeating experiments one typically observes that the time axis is deformed in a non-linear way. In this paper we propose a technique to align the time series based on generalized canonical correlation analysis (GCCA) for multiple datasets. The monotonicity constraint in time series alignment is incorporated in the GCCA algorithm. The alignment function is learned both in a supervised and a semi-supervised fashion. We compare our approach with previously published methods for aligning mass spectrometry data on a large proteomics dataset.
BibTeX:
@inproceedings{fischerRothBuhmann:07a,
  author = {Bernd Fischer and Volker Roth and Joachim M. Buhmann},
  title = {Time-Series Alignment by Non-Negative Multiple Generalized Canonical Correlation Analysis},
  booktitle = {Computational Intelligence Methods for Bioinformatics and Biostatistics},
  publisher = {Springer},
  year = {2007},
  volume = {4578},
  pages = {505--511},
  url = {http://dx.doi.org/10.1007/978-3-540-73400-0_64}
}
Frey, H.-P., König, P. & Einhäuser, W. The Role of First- and Second Order Stimulus Features for Human Overt Attention 2007 Perception and Psychophysics   article PDF  
Abstract: When processing complex visual input, human observers sequentially allocate their attention to different subsets of the stimulus. What are the mechanisms and strategiesthat guide this selection process? Here we investigate the influence of various stimulus features on human overt attention, i.e. attention related to shifts of gaze, innatural color images and modified versions thereof. The modifications, systematic changes of hue across the entire image, influence only the global appearance of thestimuli, while leaving the local features under investigation unaffected. We demonstrate that the modifications reduce the subjective interpretation of a stimulus as ''natural'' consistently across observers. By analyzing fixations, we find that firstorder features, such as luminance-contrast, saturation and color-contrast along either of the cardinal axes, are correlated to overt attention in the modified images. In contrast, no such correlation is found in unmodified outdoor images. Second-order luminance-contrast (''texture-contrast'') is correlated to overt attention in all conditions. However, none of the second-order color-contrasts are correlated to overt attention in unmodified images while one of the second-order color-contrasts exhibits a significant correlation in modified images. These findings, on the one hand, imply that higher order bottom-up effects, namely those of second-order luminance-contrast, may partly account for human overt attention. On the other hand, these results also demonstrate that global images properties, which correlate to the subjective impression of a scene as being ''natural'', affect the guidance of human overt attention.
BibTeX:
@article{Frey2007,
  author = {Hans-Peter Frey and Peter K\"onig and Wolfgang Einh\"auser},
  title = {The Role of First- and Second Order Stimulus Features for Human Overt Attention},
  journal = {Perception and Psychophysics},
  year = {2007},
  volume = {69},
  number = {2},
  pages = {153--161}
}
Grossmann$^, J., Fischer$^, B., Bärenfaller, K., Owitil, J., Buhmann, J. M., Gruissem, W. & Baginsky, S. A workflow to increase the detection rate of proteins from un-sequenced organisms inhigh-throughput proteomics experiments 2007 Proteomics   article URL  
Abstract: We present and evaluate a strategy for the mass spectrometric identification of proteins from organisms for which no genome sequence information is available that incorporates cross-species information from sequenced organisms. The presented method combines spectrum quality scoring, de novo sequencing and error tolerant BLAST searches and is designed to decrease input data complexity. Spectral quality scoring reduces the number of investigated mass spectra without a loss of information. Stringent quality-based selection and the combination of different de novo sequencing methods substantially increase the catalog of significant peptide alignments. The de novo sequences passing a reliability filter are subsequently submitted to error tolerant BLAST searches and MS-BLAST hits are validated by a sampling technique. With the described workflow, we identified up to 20% more groups of homologous proteins in proteome analyses with organisms whose genome is not sequenced than by state-of-the-art database searches in an Arabidopsis thaliana database. We consider the novel data analysis workflow an excellent screening method to identify those proteins that evade detection in proteomics experiments as a result of database constraints.
BibTeX:
@article{grossmann.fischer.ea:workflow,
  author = {Jonas Grossmann$^\ast$ and Bernd Fischer$^\ast$ and Katja B\"arenfaller and Judith Owitil and Joachim M. Buhmann and Wilhelm Gruissem and Sacha Baginsky},
  title = {A workflow to increase the detection rate of proteins from un-sequenced organisms inhigh-throughput proteomics experiments},
  journal = {Proteomics},
  year = {2007},
  volume = {7},
  number = {23},
  pages = {4245 -- 4254},
  note = {$^\ast$authors contributed equally},
  url = {http://dx.doi.org/10.1002/pmic.200700474}
}
Kaynig, V., Fischer, B., Wepf, R. & Buhmann, J. M. Fully Automatic Registration of Electron Microscopy Images with High and Low Resolution 2007 Microscopy and Microanalysis   inproceedings URL  
BibTeX:
@inproceedings{Kaynig2007,
  author = {Verena Kaynig and Bernd Fischer and Roger Wepf and Joachim M. Buhmann},
  title = {Fully Automatic Registration of Electron Microscopy Images with High and Low Resolution},
  booktitle = {Microscopy and Microanalysis},
  year = {2007},
  url = {http://journals.cambridge.org/action/displayAbstract?fromPage=online&aid=1213224#}
}
Lange, T. & Buhmann, J. M. Regularized Data Fusion Improves Image Segmentation 2007 Pattern Recognition - Symposium of the DAGM 2007   inproceedings  
BibTeX:
@inproceedings{Lange2007,
  author = {Tilman Lange and Joachim M. Buhmann},
  title = {Regularized Data Fusion Improves Image Segmentation},
  booktitle = {Pattern Recognition - Symposium of the DAGM 2007},
  publisher = {Springer},
  year = {2007},
  volume = {4713},
  pages = {234-243}
}
Lange, T. & Buhmann, J. M. Kernel-Based Grouping of Histogramm Data 2007 ECML 2007   inproceedings  
BibTeX:
@inproceedings{Lange2007b,
  author = {Tilman Lange and Joachim M. Buhmann},
  title = {Kernel-Based Grouping of Histogramm Data},
  booktitle = {ECML 2007},
  year = {2007},
  note = {(to be published)}
}
Ommer, B. & Buhmann, J. M. Learning the Compositional Nature of Visual Objects 2007 CVPR 2007   inproceedings  
BibTeX:
@inproceedings{Ommer2007,
  author = {Bj\"orn Ommer and Joachim M. Buhmann},
  title = {Learning the Compositional Nature of Visual Objects},
  booktitle = {CVPR 2007},
  year = {2007},
  note = {(in press)}
}
Ommer, B. & Buhmann, J. M. Compositional Object Recognition, Segmentation, and Tracking in Video 2007 International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'07)   inproceedings PDF  
BibTeX:
@inproceedings{Ommer2007a,
  author = {Bj\"orn Ommer and Joachim M. Buhmann},
  title = {Compositional Object Recognition, Segmentation, and Tracking in Video},
  booktitle = {International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'07)},
  publisher = {Springer},
  year = {2007},
  volume = {4679},
  pages = {318-333}
}
Orbanz, P., Braendle, S. & Buhmann, J. M. Bayesian Order-Adaptive Clustering for Video Segmentation 2007 EMMCVPR 2007   inproceedings PDF  
Abstract: Video segmentation requires the partitioning of a series ofimages into groups that are both spatially coherent and smooth along the time axis. We formulate segmentation as a Bayesian clustering problem. Context information is propagated over time by a conjugate structure. The level of segment resolution is controlled by a Dirichlet process prior. Our contributions include a conjugate nonparametric Bayesian model for clustering in multivariate time series, a MCMC inference algorithm, and a multiscale sampling approach for Dirichlet process mixture models. The multiscale algorithm is applicable to data with a spatial structure.The method is tested on synthetic data and on videos from the MPEG4 benchmark set.
BibTeX:
@inproceedings{Orbanz2007b,
  author = {Peter Orbanz and Samuel Braendle and Joachim M. Buhmann},
  title = {Bayesian Order-Adaptive Clustering for Video Segmentation},
  booktitle = {EMMCVPR 2007},
  publisher = {Springer},
  year = {2007},
  pages = {334--349}
}
Pellet, J. P. & Elisseeff, A. A Partial Correlation-Based Algorithm for Causal Structure Discovery with Continuous Variables 2007 Advances in Intelligent Data Analysis VII, 7th International Symposium on Intelligent Data Analysis   inproceedings PDF  
Abstract: We present an algorithm for causal structure discovery suited in the presence of continuous variables. We test a version based on partial correlation that is able to recover the structure of a recursive linear equations model and compare it to the well-known PC algorithm on large networks. PC is generally outperformed in run time and number of structural errors.
BibTeX:
@inproceedings{pellet07ida,
  author = {Jean Philippe Pellet and Andr\'{e} Elisseeff},
  title = {A Partial Correlation-Based Algorithm for Causal Structure Discovery with Continuous Variables},
  booktitle = {Advances in Intelligent Data Analysis VII, 7th International Symposium on Intelligent Data Analysis},
  year = {2007},
  pages = {229--239}
}
Roos, F. F., Jacob, R., Grossmann, J., Fischer, B., Buhmann, J., Gruissem, W., Baginsky, S. & Widmayer, P. PepSplice: Cache-Efficient Search Algorithms for Comprehensive Identification of Tandem Mass Spectra 2007 Bioinformatics   article URL  
Abstract: bf Motivation: Tandem mass spectrometry allows for high-throughput identification of complex protein samples. Searching tandem mass spectra against sequence databases is the main analysis method nowadays. Since many peptide variations are possible, including them in the search space seems only logical. However, the search space usually grows exponentially with the number of independent variations and may therefore overwhelm computational resources.\ bf Results: We provide fast, cache-efficient search algorithms to screen large peptide search spaces including non-tryptic peptides, whole genomes, dozens of posttranslational modifications, unannotated point mutations and even unannotated splice sites. All these search spaces can be screened simultaneously. By optimizing the cache usage, we achieve a calculation speed that closely approaches the limits of the hardware. At the same time, we control the size of the overall search space by limiting the combinations of variations that can co-occur on the same peptide. Using a hypergeometric scoring scheme, we applied these algorithms to a dataset of 1 420 632 spectra. We were able to identify a considerable number of peptide variations within a modest amount of computing time on standard desktop computers.\ bf Availability: PepSplice is available as a C++ application for Linux, Windows and OSX at www.ti.inf.ethz.ch/pw/software/pepsplice/. It is open source under the revised BSD license.
BibTeX:
@article{roos.jacob.ea:pepsplice,
  author = {Franz F. Roos and Riko Jacob and Jonas Grossmann and Bernd Fischer and Joachim Buhmann and Wilhelm Gruissem and Sacha Baginsky and Peter Widmayer},
  title = {PepSplice: Cache-Efficient Search Algorithms for Comprehensive Identification of Tandem Mass Spectra},
  journal = {Bioinformatics},
  year = {2007},
  volume = {23},
  number = {22},
  pages = {3016--3023},
  note = {$^\ast$authors contributed equally},
  url = {http://dx.doi.org/10.1093/bioinformatics/btm417}
}
Roth, V. & Fischer, B. The kernelHMM: Learning Kernel Combinations in Structured Output Domains 2007 Pattern Recognition (29th DAGM Symposium)   inproceedings URL  
Abstract: We present a model for learning convex kernel combinations in classification problems with structured output domains. The main ingredient is a hidden Markov model which forms a layered directed graph. Each individual layer represents a multilabel version of nonlinear kernel discriminant analysis for estimating the emission probabilities. These kernel learning machines are equipped with a mechanism for finding convex combinations of kernel matrices. The resulting kernelHMM can handle multiple partial paths through the label hierarchy in a consistent way. Efficient approximation algorithms allow us to train the model to large-scale learning problems. Applied to the problem of document categorization, the method exhibits excellent predictive performance.
BibTeX:
@inproceedings{Roth2007,
  author = {Volker Roth and Bernd Fischer},
  title = {The kernelHMM: Learning Kernel Combinations in Structured Output Domains},
  booktitle = {Pattern Recognition (29th DAGM Symposium)},
  publisher = {Springer},
  year = {2007},
  volume = {4713},
  pages = {436--445},
  url = {http://www.springerlink.com/content/r015664w85831633/fulltext.pdf}
}
Roth, V. & Fischer, B. Improved Functional Prediction of Proteins by Learning Kernel Combinations in Multilabel Settings 2007 BMC Bioinformatics   article URL  
Abstract: bf Background: We develop a probabilistic model for combining kernel matrices to predict the function of proteins. It extends previous approaches in that it can handle multiple labels which naturally appear in the context of protein function.\ bf Results: Explicit modeling of multilabels significantly improves the capability of learning protein function from multiple kernels. The performance and the interpretability of the inference model are further improved by simultaneously predicting the subcellular localization of proteins and by combining pairwise classifiers to consistent class membership estimates.\ bf Conclusion: For the purpose of functional prediction of proteins, multilabels provide valuable information that should be included adequately in the training process of classifiers. Learning of functional categories gains from co-prediction of subcellular localization. Pairwise separation rules allow very detailed insights into the relevance of different measurements like sequence, structure, interaction data, or expression data. A preliminary version of the software can be downloaded from http://www.inf.ethz.ch/personal/vroth/KernelHMM/
BibTeX:
@article{rothFischer:07a,
  author = {Volker Roth and Bernd Fischer},
  title = {Improved Functional Prediction of Proteins by Learning Kernel Combinations in Multilabel Settings},
  journal = {BMC Bioinformatics},
  year = {2007},
  volume = {8},
  number = {S2},
  pages = {S12},
  url = {http://dx.doi.org/10.1186/1471-2105-8-S2-S12}
}
Sigg, C., Fischer, B., Ommer, B., Roth, V. & Buhmann, J. Nonnegative CCA for Audiovisual Source Separation 2007 IEEE Workshop on Machine Learning for Signal Processing   inproceedings PDF  
Abstract: We present a method for finding correlated components in audio and video signals. The new technique is applied to the task of identifying sources in video and separating them in audio. The concept of canonical correlation analysis is reformulated such that it incorporates nonnegativity and sparsity constraints on the coefficients of projection directions. Nonnegativity ensures that projections are compatible with an interpretation as energy signals. Sparsity ensures that coefficient weight concentrates on individual sources. By finding multiple conjugate directions we finally obtain a component based decomposition of both data modalities. Experiments effectively demonstrate the potential and benefits of this approach.
BibTeX:
@inproceedings{Sigg2007,
  author = {Christian Sigg and Bernd Fischer and Bjoern Ommer and Volker Roth and Joachim Buhmann},
  title = {Nonnegative CCA for Audiovisual Source Separation},
  booktitle = {IEEE Workshop on Machine Learning for Signal Processing},
  publisher = {IEEE Press},
  year = {2007}
}
Zöller, T. & Buhmann, J. M. Robust Image Segmentation using Resampling and Shape Constraints 2007 IEEE Transactions on Pattern Analysis and Machine Intelligence   article  
BibTeX:
@article{Zoller2007,
  author = {Thomas Z\"oller and Joachim M. Buhmann},
  title = {Robust Image Segmentation using Resampling and Shape Constraints},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2007},
  note = {(in press)}
}
Fischer, B., Grossmann, J., Roth, V., Gruissem, W., Baginsky, S. & Buhmann, J. M. Semi-Supervised LC/MS Alignment for Differential Proteomics 2006 Bioinformatics   article URL PDF  
Abstract: Motivation: Mass spectrometry (MS) combined with high-performance liquid chromatography (LC) has received considerable attention for high-throughput analysis of proteomes. Isotopic labeling techniques such as ICAT have been successfully applied to derive differential quantitative information for two protein samples, however at the price of significantly increased complexity of the experimental setup. To overcome these limitations, we consider a label-free setting where correspondences between elements of two samples have to be established prior to the comparative analysis. The alignment between samples is achieved by nonlinear robust ridge regression. The correspondence estimates are guided in a semi-supervised fashion by prior information which is derived from sequenced tandem mass spectra.Results: The semi-supervised method for finding correspondences was successfully applied to aligning highly complex protein samples, even if they exhibit large variations due to different biological conditions. A large-scale experiment clearly demonstrates that the proposed method bridges the gap between statistical data analysis and label-free quantitative differential proteomics.Availability: The software will be available on the website http://people.inf.ethz.ch/befische/proteomics
BibTeX:
@article{fischer.grossmann.ea:semi-supervised,
  author = {Bernd Fischer and Jonas Grossmann and Volker Roth and Wilhelm Gruissem and Sacha Baginsky and Joachim M. Buhmann},
  title = {Semi-Supervised LC/MS Alignment for Differential Proteomics},
  journal = {Bioinformatics},
  year = {2006},
  volume = {22},
  number = {14},
  pages = {e132--e140},
  url = {http://dx.doi.org/10.1093/bioinformatics/btl219}
}
Keuchel, J. & Küttel, D. Efficient Combination of Probabilistic Sampling Approximations for Robust Image Segmentation 2006 Pattern Recognition (28th DAGM Symposium)   inproceedings  
BibTeX:
@inproceedings{Keuchel2006,
  author = {J. Keuchel and D. K{\"u}ttel},
  title = {Efficient Combination of Probabilistic Sampling Approximations for Robust Image Segmentation},
  booktitle = {Pattern Recognition (28th DAGM Symposium)},
  publisher = {Springer},
  year = {2006},
  volume = {4174},
  pages = {41-50}
}
Keuchel, J. Multiclass Image Labeling with Semidefinite Programming 2006 Computer Vision -- ECCV 2006   inproceedings  
BibTeX:
@inproceedings{Keuchel2006a,
  author = {Jens Keuchel},
  title = {Multiclass Image Labeling with Semidefinite Programming},
  booktitle = {Computer Vision -- ECCV 2006},
  publisher = {Springer},
  year = {2006},
  volume = {3952},
  pages = {454-467}
}
Lange, T. & Buhmann, J. Fusion of Similarity Data in Clustering 2006 Advances in Neural Information Processing Systems (NIPS) 19   inproceedings  
BibTeX:
@inproceedings{Lange2006,
  author = {Tilman Lange and Joachim Buhmann},
  title = {Fusion of Similarity Data in Clustering},
  booktitle = {Advances in Neural Information Processing Systems (NIPS) 19},
  publisher = {MIT Press},
  year = {2006},
  pages = {723-730}
}
Laub, J., Roth, V., Buhmann, J. M. & Müller, K.-R. On the Information and Representation of Non-Euclidean Pairwise Data 2006 Pattern Recognition   article  
BibTeX:
@article{Laub2006,
  author = {Julian Laub and Volker Roth and Joachim M. Buhmann and Klaus-Robert M\"uller},
  title = {On the Information and Representation of Non-Euclidean Pairwise Data},
  journal = {Pattern Recognition},
  year = {2006},
  volume = {39},
  pages = {1815-1826}
}
Ommer, B., Sauter, M. & Buhmann, J. M. Learning Top-Down Grouping of Compositional Hierarchies for Recognition 2006 CVPR'06 (POCV)   inproceedings PDF  
Abstract: The complexity of real world image categorization and scene analysis requires compositional strategies for object representation. This contribution establishes a ompositionalhierarchy by first performing a perceptual bottom-up grouping of edge pixels to generate salient contour curves. A subsequent recursive top-down grouping yields a hierarchy of compositions. All entities in the compositional hierarchy are incorporated in a Bayesian network that couples them together by means of a shape model. The probabilistic model underlying top-down grouping as well as the shape model is learned automatically from a set of training images for the given categories. As a consequence, compositionality simplifies the learning of complex category models by building them from simple, frequently used compositions. The architecture is evaluated on the highly challenging Caltech 101 database which exhibits large intra-category variations. The proposed compositional approach shows competitive retrieval rates in the range of 53.0 ± 0.49%.
BibTeX:
@inproceedings{Ommer2006,
  author = {Bj\"orn Ommer and Michael Sauter and Joachim M. Buhmann},
  title = {Learning Top-Down Grouping of Compositional Hierarchies for Recognition},
  booktitle = {CVPR'06 (POCV)},
  year = {2006}
}
Ommer, B. & Buhmann, J. M. Learning Compositional Categorization Models 2006 ECCV'06   inproceedings PDF  
Abstract: This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database and form intermediate abstractions of images that are semantically situated between low-level representations and the high-level categorization. Salient regions, which are described by localized feature histograms, are detected as image parts. Subsequently compositions are formed as bags of parts with a locality constraint. After performing a spatial binding of compositions by means of a shape model, coupled probabilistic kernel classifiers are applied thereupon to establish the final image categorization. In contrast to the discriminative training of the categorizer, intermediate compositions are learned in a generative manner yielding relevant part agglomerations, i.e. groupings which are frequently appearing in the dataset while simultaneously supporting the discrimination between sets of categories. Consequently, compositionality simplifies the learning of a complex categorization model for complete scenes by splitting it up into simpler, sharable compositions. The architecture is evaluated on the highly challenging Caltech 101 database which exhibits large intra-category variations. Our compositional approach shows competitive retrieval rates in the range of 53.6±0.88% or, with a multi-scale feature set, rates of 57.8 ± 0.79%.
BibTeX:
@inproceedings{Ommer2006a,
  author = {Bj\"orn Ommer and Joachim M. Buhmann},
  title = {Learning Compositional Categorization Models},
  booktitle = {ECCV'06},
  publisher = {LNCS 3953, Springer},
  year = {2006}
}
Orbanz, P. & Buhmann, J. M. Smooth Image Segmentation by Nonparametric Bayesian Inference 2006 European Conference on Computer Vision (ECCV 2006)   inproceedings  
BibTeX:
@inproceedings{Orbanz2006,
  author = {Peter Orbanz and Joachim M. Buhmann},
  title = {Smooth Image Segmentation by Nonparametric Bayesian Inference},
  booktitle = {European Conference on Computer Vision (ECCV 2006)},
  publisher = {Springer Verlag},
  year = {2006},
  volume = {I},
  pages = {444-457}
}
Peter, H., Fischer, B. & Buhmann, J. M. Probabilistic De Novo Peptide Sequencing with Doubly Charged Ions 2006 Pattern Recognition - Symposium of the DAGM 2006   inproceedings URL PDF  
Abstract: Sequencing of peptides by tandem mass spectrometry has matured to the key technology for proteomics. Noise in the measurement process strongly favors statistical models like NovoHMM, a recently published generative approach based on factorial hidden Markov models. We extend this hidden Markov model to include information of doubly charged ions since the original model can only cope with singly charged ions. This modification requires a refined discretization of the mass scale and, thereby, it increases its sensitivity and recall performance on a number of datasets to compare favorably with alternative approaches for mass spectra interpretation.
BibTeX:
@inproceedings{peter.fischer.ea:probabilistic,
  author = {Hansruedi Peter and Bernd Fischer and Joachim M. Buhmann},
  title = {Probabilistic De Novo Peptide Sequencing with Doubly Charged Ions},
  booktitle = {Pattern Recognition - Symposium of the DAGM 2006},
  publisher = {Springer},
  year = {2006},
  volume = {4174},
  pages = {424--433},
  url = {http://dx.doi.org/10.1007/11861898_43}
}
Rabinovich, A., Lange, T., Buhmann, J. & Belongie, S. Model Order Selection and Cue Combination for Image Segmentation 2006 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006)   inproceedings  
BibTeX:
@inproceedings{Rabinovich2006,
  author = {A. Rabinovich and T. Lange and J. Buhmann and S. Belongie},
  title = {Model Order Selection and Cue Combination for Image Segmentation},
  booktitle = {2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006)},
  publisher = {IEEE Computer Society},
  year = {2006},
  pages = {1130-1137}
}
Roth, V. Kernel Fisher Discriminants for Outlier Detection 2006 Neural Computation   article PDF  
Abstract: he problem of detecting ``atypical objects'' or ``outliers'' is one of the classical topics in (robust) statistics. Recently, it has been proposed to address this problem by means of one-class SVM classifiers. The method presented in this paper bridges the gap between kernelized one-class classification and Gaussian density estimation in the induced feature space. Having established the exact relation between the two concepts, it is now possible to identify ``atypical objects'' by quantifying their deviations from the Gaussian model. This model-based formalization of outliers overcomes the main conceptual shortcoming of most one-class approaches which, in a strict sense, are unable to detect outliers, since the expected fraction of outliers has to be specified in advance. In order to overcome the inherent model selection problem of unsupervised kernel methods, a cross-validated likelihood criterion for selecting all free model parameters is applied. Experiments for detecting atypical objects in image databases effectively demonstrate the applicability of the proposed method in real world scenarios.
BibTeX:
@article{Roth2006,
  author = {Volker Roth},
  title = {Kernel Fisher Discriminants for Outlier Detection},
  journal = {Neural Computation},
  year = {2006},
  volume = {18},
  number = {4}
}
Roth, V. & Ommer, B. Exploiting Low-level Image Segmentation for Object Recognition 2006 Pattern Recognition--DAGM 2006   inproceedings PDF  
Abstract: A method for exploiting the information in low-level image segmentations for the purpose of object recognition is presented. The key idea is to use a whole ensemble of segmentations per image, computed on different random samples of image sites. Along the boundaries of those segmentations that are stable under the sampling process we extract strings of vectors that contain local image descriptors like shape, texture and intensities. Pairs of such strings are aligned, and based on the alignment scores a mixture model is trained which divides the segments in an image into fore- and background. Given such candidate foreground segments, we show that it is possible to build a state-of-the-art object recognition system that exhibits excellent performance on a standard benchmark database. This result shows that despite the inherent problems of low-level image segmentation in poor data conditions, segmentation can indeed be a valuable tool for object recognition in real-world images.
BibTeX:
@inproceedings{Roth2006a,
  author = {Volker Roth and Bj{\"o}rn Ommer},
  title = {Exploiting Low-level Image Segmentation for Object Recognition},
  booktitle = {Pattern Recognition--DAGM 2006},
  publisher = {Springer},
  year = {2006},
  volume = {4174}
}
Roth, V. & Fischer, B. Improved Functional Prediction of Proteins by Learning Kernel Combinations in Multilabel Settings 2006   techreport PDF  
Abstract: A method for learning kernel combinations is presented which explicitly addresses the problem of multilabel classification in which an object can belong to more than one class. Such multilabels appear naturally in the context of protein function prediction, since a protein can be involved in several different biological processes exhibiting more than one function.
BibTeX:
@techreport{Roth2006b,
  author = {Volker Roth and Bernd Fischer},
  title = {Improved Functional Prediction of Proteins by Learning Kernel Combinations in Multilabel Settings},
  year = {2006},
  number = {B-2006-4},
  note = {Proceeding of PMSB 2006}
}
Steinhage, V., Schröder, S., Roth, V., Cremers, A., Drescher, W. & Wittmann, D. The Sience of Fingerprinting Bees 2006 German Research   article PDF  
Abstract: The ABIS system allows the rapid and accurate identification of bee species. This process is based on automatic image analysis of the bee's wings and enables the development of new, computer-aided methods to identify the bee species.
BibTeX:
@article{Steinhage2006,
  author = {V. Steinhage and S. Schr{\"o}der and V. Roth and A.B. Cremers and W. Drescher and D. Wittmann},
  title = {The Sience of Fingerprinting Bees},
  journal = {German Research},
  year = {2006},
  volume = {28},
  number = {1aa},
  pages = {19-21}
}
Wey, P., Fischer, B., Bay, H. & Buhmann, J. M. Dense Stereo by Triangular Meshing and Cross Validation 2006 Pattern Recognition - Symposium of the DAGM 2006   inproceedings URL PDF  
Abstract: Dense depth maps can be estimated in a Bayesian sense from multiple calibrated still images of a rigid scene relative to a reference view. This well-established probabilistic framework is extended by adaptively refining a triangular meshing procedure and by automatic cross-validation of model parameters. The adaptive refinement strategy locally adjusts the triangular meshing according to the measured image data. The new method substantially outperforms the competing techniques both in terms of robustness and accuracy.
BibTeX:
@inproceedings{wey.fischer.ea:dense,
  author = {Peter Wey and Bernd Fischer and Herbert Bay and Joachim M. Buhmann},
  title = {Dense Stereo by Triangular Meshing and Cross Validation},
  booktitle = {Pattern Recognition - Symposium of the DAGM 2006},
  publisher = {Springer},
  year = {2006},
  volume = {4174},
  pages = {708--717},
  url = {http://dx.doi.org/10.1007/11861898_71}
}
Buhmann, J. M., Lange, T. & Ramacher, U. Image Segmentation by Networks of Spiking Neurons 2005 Neural Computation   article  
BibTeX:
@article{Buhmann2005,
  author = {Joachim M. Buhmann and Tilman Lange and Ulrich Ramacher},
  title = {Image Segmentation by Networks of Spiking Neurons},
  journal = {Neural Computation},
  year = {2005},
  volume = {17},
  number = {5},
  pages = {1010-1031}
}
Fischer, B., Roth, V., Buhmann, J. M., Grossmann, J., Baginsky, S., Gruissem, W., Roos, F. & Widmayer, P. A Hidden Markov Model for de Novo Peptide Sequencing 2005 Neural Information Processing Systems   article URL PDF  
Abstract: De novo Sequencing of peptides is a challenging task in proteome research. While there exist reliable DNA-sequencing methods, the highthroughput de novo sequencing of proteins by mass spectrometry is still an open problem. Current approaches suffer from a lack in precision to detect mass peaks in the spectrograms. In this paper we present a novel method for de novo peptide sequencing based on a hidden Markov model. Experiments effectively demonstrate that this new method significantly outperforms standard approaches in matching quality.
BibTeX:
@article{fischer.roth.ea:hidden,
  author = {Bernd Fischer and Volker Roth and Joachim M. Buhmann and Jonas Grossmann and Sacha Baginsky and Wilhelm Gruissem and Franz Roos and Peter Widmayer},
  title = {A Hidden Markov Model for de Novo Peptide Sequencing},
  journal = {Neural Information Processing Systems},
  year = {2005},
  volume = {17},
  pages = {457--464},
  url = {http://books.nips.cc/papers/files/nips17/NIPS2004_0372.pdf}
}
Fischer, B., Roth, V., Roos, F., Grossmann, J., Baginsky, S., Widmayer, P., Gruissem, W. & Buhmann, J. M. NovoHMM: A Hidden Markov Model for de Novo Peptide Sequencing 2005 Analytical Chemistry   article URL PDF  
Abstract: De novo sequencing of peptides poses one of the most challenging tasks in data analysis for proteome research. In this paper, a generative hidden Markov model (HMM) of mass spectra for de novo peptide sequencing which constitutes a novel view on how to solve this problem in a Bayesian framework is proposed. Further extensions of the model structure to a graphical model and a factorial HMM to substantially improve the peptide identification results are demonstrated. Inference with the graphical model for de novo peptide sequencing estimates posterior probabilities for amino acids rather than scores for single symbols in the sequence. Our model outperforms state-of-the-art methods for de novo peptide sequencing on a large test set of spectra.
BibTeX:
@article{fischer.roth.ea:novohmm,
  author = {Bernd Fischer and Volker Roth and Franz Roos and Jonas Grossmann and Sacha Baginsky and Peter Widmayer and Wilhelm Gruissem and Joachim M. Buhmann},
  title = {NovoHMM: A Hidden Markov Model for de Novo Peptide Sequencing},
  journal = {Analytical Chemistry},
  year = {2005},
  volume = {77},
  number = {22},
  pages = {7265-7273},
  url = {http://dx.doi.org/10.1021/ac0508853}
}
Heiler, M., Keuchel, J. & Schnörr, C. Semidefinite Clustering for Image Segmentation with A-priori Knowledge 2005 Pattern Recognition (27th DAGM Symposium)   inproceedings  
BibTeX:
@inproceedings{Heiler2005,
  author = {M. Heiler and J. Keuchel and C. Schn{\"o}rr},
  title = {Semidefinite Clustering for Image Segmentation with A-priori Knowledge},
  booktitle = {Pattern Recognition (27th DAGM Symposium)},
  publisher = {Springer},
  year = {2005},
  volume = {3663},
  pages = {309-317}
}
Lange, T., Law, M. H. C., Jain, A. K. & Buhmann, J. M. Learning with Constrained and Unlabelled Data 2005 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005)   inproceedings  
BibTeX:
@inproceedings{Lange2005,
  author = {Tilman Lange and Martin H. C. Law and Anil K. Jain and Joachim M. Buhmann},
  title = {Learning with Constrained and Unlabelled Data},
  booktitle = {2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005)},
  publisher = {IEEE Computer Society},
  year = {2005},
  pages = {731-738}
}
Lange, T. & Buhmann, J. Combining partitions by probabilistic label aggregation 2005 KDD, Proceedings of the Eleventh ACM SIGKDD International onference on Knowledge Discovery and Data Mining   inproceedings  
BibTeX:
@inproceedings{Lange2005a,
  author = {Tilman Lange and Joachim Buhmann},
  title = {Combining partitions by probabilistic label aggregation},
  booktitle = {KDD, Proceedings of the Eleventh ACM SIGKDD International onference on Knowledge Discovery and Data Mining},
  publisher = {ACM},
  year = {2005},
  pages = {147-156}
}
Ommer, B. & Buhmann, J. M. Object Categorization by Compositional Graphical Models 2005 Energy Minimization Methods in Computer Vision and Pattern Recognition, LNCS 3757   inbook PDF  
Abstract: This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered real-world scenes. We propose a sparse image representation based on localized feature histograms of salient regions. Category specific information is then aggregated by using relations from perceptual organization to form compositions of these descriptors. The underlying concept of image region aggregation to condense semantic information advocates for a statistical representation founded on graphical models. On the basis of this structure, objects and their constituent parts are localized. To complement the learned dependencies between compositions and categories, a global shape model of all compositions that form an object is trained. During inference, belief propagation reconciles bottom-up feature-driven categorization with top-down category models. The system achieves a competitive recognition performance on the standard CalTech database.
BibTeX:
@inbook{Ommer2005,
  author = {Bj\"orn Ommer and Joachim M. Buhmann},
  title = {Object Categorization by Compositional Graphical Models},
  booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition, LNCS 3757},
  publisher = {Springer},
  year = {2005},
  pages = {235-250}
}
Orbanz, P. & Buhmann, J. M. SAR Images as Mixtures of Gaussian Mixtures 2005 Proceedings of the IEEE International Conference on Image Processing (ICIP)   inproceedings  
BibTeX:
@inproceedings{Orbanz2005,
  author = {P. Orbanz and J.~M. Buhmann},
  title = {{SAR} Images as Mixtures of {G}aussian Mixtures},
  booktitle = {Proceedings of the IEEE International Conference on Image Processing (ICIP)},
  year = {2005},
  volume = {2},
  pages = {209-212}
}
Roth, V. Outlier Detection with One-class Kernel Fisher Discriminants 2005 NIPS 17   inproceedings PDF  
Abstract: The problem of detecting “atypical objects” or “outliers” is one of the classical topics in (robust) statistics. Recently, it has been proposed to address this problem by means of one-class SVM classifiers. The main conceptual shortcoming of most one-class approaches, however, is that in a strict sense they are unable to detect outliers, since the expected fraction of outliers has to be specified in advance. The method presented in this paper overcomes this problem by relating kernelized one-class classification to Gaussian density estimation in the induced feature space. Having established this relation, it is possible to identify “atypical objects” by quantifying their deviations from the Gaussian model. For RBF kernels it is shown that the Gaussian model is “rich enough” in the sense that it asymptotically provides an unbiased estimator for the true density. In order to overcome the inherent model selection problem, a cross-validated likelihood criterion for selecting all free model parameters is applied.
BibTeX:
@inproceedings{Roth2005,
  author = {Volker Roth},
  title = {Outlier Detection with One-class Kernel Fisher Discriminants},
  booktitle = {NIPS 17},
  year = {2005}
}
Fischer, B., Roth, V. & Buhmann, J. M. Clustering with the Connectivity Kernel 2004 Neural Information Processing Systems   inproceedings URL PDF  
Abstract: Clustering aims at extracting hidden structure in dataset. While the problem of finding compact clusters has been widely studied in the literature, extracting arbitrarily formed elongated structures is considered a much harder problem. In this paper we present a novel clustering algorithm which tackles the problem by a two step procedure: first the data are transformed in such a way that elongated structures become compact ones. In a second step, these new objects are clustered by optimizing a compactness-based criterion. The advantages of the method over related approaches are threefold: (i) robustness properties of compactness-based criteria naturally transfer to the problem of extracting elongated structures, leading to a model which is highly robust against outlier objects; (ii) the transformed distances induce a Mercer kernel which allows us to formulate a polynomial approximation scheme to the generally NP-hard clustering problem; (iii) the new method does not contain free kernel parameters in contrast to methods like spectral clustering or mean-shift clustering.
BibTeX:
@inproceedings{fischer.roth.ea:clustering,
  author = {Bernd Fischer and Volker Roth and Joachim M. Buhmann},
  title = {Clustering with the Connectivity Kernel},
  booktitle = {Neural Information Processing Systems},
  publisher = {MIT Press},
  year = {2004},
  volume = {16},
  url = {http://books.nips.cc/papers/files/nips16/NIPS2003_AA12.pdf}
}
Hermes, L. & Buhmann, J. Boundary-Constrained Agglomerative Segmantation 2004 IEEE Transactions on Geoscience and Remote Sensing   inproceedings PDF  
Abstract: Automated interpretation of remotely sensed dataposes certain demands to image segmentation algorithms, regarding speed, memory requirements, segmentation quality, noise robustness, complexity, and reproducibility. This paper addresses these issues by formulating image segmentation as source channel coding with side information. A cost function is developed thatapproximates the expected code length for a hypothetical two-part coding scheme. The cost function combines region-based and edge-based considerations, and it supports the utilization of reference data to enhance segmentation results. Optimization is implemented by an agglomerative segmentation algorithm that iteratively creates a tree-like description of the image. Given a fixed tree level and the output of the edge detector, the cost functionis parameter-free, so that no exhaustive parameter-tuning is necessary. Additionally, a criterion is presented to reliably select an adequate tree level with high descriptive quality. It is shown by statistical analysis that the cost function is appropriate for both multispectral and synthetic aperture radar data. Experimental results confirm the high quality of the resulting segmentations.
BibTeX:
@inproceedings{Hermes2004,
  author = {Lothar Hermes and Joachim Buhmann},
  title = {Boundary-Constrained Agglomerative Segmantation},
  booktitle = {IEEE Transactions on Geoscience and Remote Sensing},
  publisher = {IEEE},
  year = {2004},
  volume = {42}
}
Jain, A. K., Topchy, A., Law, M. H. & Buhmann, J. M. Landscape of Clustering Algorithms 2004 17th International Conference on Pattern Recognition Cambridge UK   inproceedings PDF  
Abstract: Numerous clustering algorithms, their taxonomies and evaluation studies are available in the literature. Despite the diversity of different clustering algorithms, solutions delivered by these algorithms exhibit many commonalities. An analysis of the similarity and properties of clustering objective functions is necessary from the operational/user perspective. We revisit conventional categorization of clustering algorithms and attempt to relate them according to the partitions they produce. We empirically study the similarity of clustering solutions obtained by many traditional as well as relatively recent clustering algorithms on a number of real-world data sets. Sammon’s mapping and a complete-link clustering of the inter-clustering dissimilarity values are performed to detect a meaningful grouping of the objective functions. We find that only a small number of clustering algorithms are sufficient to represent a large spectrum of clustering criteria. For example, interesting groups of clustering algorithms are centered around the graph partitioning, linkage-based and Gaussian mixture model based algorithms.
BibTeX:
@inproceedings{Jain2004,
  author = {Anil K. Jain and Alexander Topchy and Martin H.C. Law and Joachim M. Buhmann},
  title = {Landscape of Clustering Algorithms},
  booktitle = {17th International Conference on Pattern Recognition Cambridge UK},
  publisher = {IEEE},
  year = {2004},
  pages = {I-260--I-263}
}
Lange, T., Roth, V., Braun, M. L. & Buhmann, J. M. Stability-Based Validation of Clustering Solutions 2004 Neural Computation   article PDF  
Abstract: Data clustering describes a set of frequently employed techniques in exploratory data analysis to extract “natural” group structure in data. Such groupings need to be validated to separate the signal in the data from spurious structure. In this context, finding an appropriate number of clustersis a particularly important model selection question.We introduce a measure of cluster stability to assess the validity of a cluster model. This stability measure quantifies the reproducibility of clustering solutionson a second sample, and it can be interpreted as a classification risk with regard to class labels produced by a clustering algorithm. The preferred number of clusters is determined by minimizing this classification risk as a function of the number of clusters. Convincing results are achieved on simulated as well as gene expression data sets. Comparisons to other methods demonstrate the competitive performance of our method and its suitability as a general validation tool for clustering solutions in realworld problems.
BibTeX:
@article{Lange2004,
  author = {Tilman Lange and Volker Roth and Mikio L. Braun and Joachim M. Buhmann},
  title = {Stability-Based Validation of Clustering Solutions},
  journal = {Neural Computation},
  year = {2004},
  volume = {16},
  pages = {1299-1323}
}
Roth, V. & Lange, T. Adaptive Feature Selection in Image Segmentation 2004 Pattern Recognition, DAGM   inproceedings PDF  
Abstract: Most image segmentation algorithms optimize some mathematical similarity criterion derived from several low-level image features. One possible way of combining different types of features, e.g. color- and texture features on different scales and/or different orientations, is to simply stack all the individualmeasurements into one high-dimensional feature vector. Due to the nature of such stacked vectors, however, only very few components (e.g. those which are defined on a suitable scale) will carry information that is relevant for the actual segmentation task.We present an approach to combining segmentation and adaptive feature selection that overcomes this relevance determination problem. Allfree model parameters of this method are selected by a resampling-based stability analysis. Experiments demonstrate that the built-in feature selection mechanismleads to stable and meaningful partitions of the images.
BibTeX:
@inproceedings{Roth2004,
  author = {Volker Roth and Tilman Lange},
  title = {Adaptive Feature Selection in Image Segmentation},
  booktitle = {Pattern Recognition, DAGM},
  publisher = {DAGM},
  year = {2004},
  pages = {9-17}
}
Roth, V. & Lange, T. Bayesian Class Discovery in Microarray Datasets 2004 IEEE Transactions on Biomedical Engineering   article PDF  
Abstract: A novel approach to class discovery in gene expressiondatasets is presented. In the context of clinical diagnosis, the central goal of class discovery algorithms is to simultaneously find putative (sub-)types of diseases and to identify informative subsets of genes with disease-type specific expression profile. Contrary to many other approaches in the literature, the method presentedimplements a wrapper strategy for feature selection, in the sense that the features are directly selected by optimizing the discriminative power of the used partitioning algorithm. The usual combinatorial problems associated with wrapper approaches are overcome by a Bayesian inference mechanism. On the technical side, wepresent an efficient optimization algorithm with guaranteed local convergence property. The only free parameter of the optimization method is selected by a resampling-based stability analysis. Experiments with Leukemia and Lymphoma datasets demonstrate that our method is able to correctly infer partitions and correspondingsubsets of genes which both are relevant in a biological sense. Moreover, the frequently observed problem of ambiguities caused by different but equally high-scoring partitions is successfully overcome by the model selection method proposed.
BibTeX:
@article{Roth2004a,
  author = {Volker Roth and Tilman Lange},
  title = {Bayesian Class Discovery in Microarray Datasets},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2004},
  volume = {51},
  number = {5}
}
Roth, V. & Lange, T. Feature Selection in Clustering Problems 2004 NIPS   inproceedings PDF  
Abstract: A novel approach to combining clustering and feature selection is presented. It implements a wrapper strategy for feature selection, in the sense that the features are directly selected by optimizing the discriminative power of the used partitioning algorithm. On the technical side, wepresent an efficient optimization algorithm with guaranteed local convergence property. The only free parameter of this method is selected by a resampling-based stability analysis. Experiments with real-world datasets demonstrate that our method is able to infer both meaningful partitions and meaningful subsets of features.
BibTeX:
@inproceedings{Roth2004b,
  author = {Volker Roth and Tilman Lange},
  title = {Feature Selection in Clustering Problems},
  booktitle = {NIPS},
  publisher = {MIT Press},
  year = {2004},
  pages = {1237-1244}
}
Steck, H. & Jaakkola, T. Predictive Discretization during Model Selection 2004 Pattern Recognition   article PDF  
Abstract: We present an approach to discretizing multivariate continuous data while learning the structure of a graphical model. We derive a joint scoring function from the principle of predictive accuracy, which inherently ensures the optimal trade-o between goodness of t and model complexity including the number of discretization levels. Using the socalled nest grid implied by the data, our scoring function depends only on the number of data points in the various discretization levels (independent of the metric used in the continuous space). Our experiments with arti cial data as well as with gene expression data show that discretization plays a crucial role regarding the resulting network structure.
BibTeX:
@article{Steck2004,
  author = {Harald Steck and Tommi Jaakkola},
  title = {Predictive Discretization during Model Selection},
  journal = {Pattern Recognition},
  publisher = {Elsevier},
  year = {2004},
  volume = {LNCS 3175},
  pages = {1-8}
}
Stilkerich, S. C. & Buhmann, J. Massively Parallel Architecture for an unsupervised Segmentation Model 2004 International Conference on Signals and Electronic Systems   inproceedings PDF  
Abstract: In this paper we propose the structure of a novel massively parallel system-on-chip (SoC) architecture for a state-of-the-art probabilistic image segmentation model. This probabilistic model is formulated on a regular Markovian pixel grid. The unique combination of algorithmic robustness, SoC and real-time processing capabilities provides a new type of image processing systems in realworld applications. The model and the SoC architecture are extensively tested by natural images. Some chip design examples are also included to finalize the contribution.
BibTeX:
@inproceedings{Stilkerich2004,
  author = {Stephan C. Stilkerich and Joachim Buhmann},
  title = {Massively Parallel Architecture for an unsupervised Segmentation Model},
  booktitle = {International Conference on Signals and Electronic Systems},
  publisher = {IEEE},
  year = {2004}
}
Zöller, T. & Buhmann, J. M. Shape Constrained Image Segmentation by Parametric Distributional Clustering 2004 Computer Society Conference on Computer Vision and Pattern Recognition   inproceedings PDF  
Abstract: The automated segmentation of images into semanticallymeaningful parts requires shape information since lowlevelfeature analysis alone often fails to reach this goal.We introduce a novel method of shape constrained imagesegmentation which is based on mixtures of feature distributions for color and texture as well as probabilistic shape knowledge. The combined approach is formulated in theframework of Bayesian statistics to account for the robustness requirement in image understanding. Experimental evidence shows that semantically meaningful segments are inferred, even when image data alone gives rise to ambiguoussegmentations.
BibTeX:
@inproceedings{Zoller2004,
  author = {Thomas Z\"oller and Joachim M. Buhmann},
  title = {Shape Constrained Image Segmentation by Parametric Distributional Clustering},
  booktitle = {Computer Society Conference on Computer Vision and Pattern Recognition},
  year = {2004},
  pages = {386-394}
}
Chen, W.-J. & Buhmann, J. M. A New Distance Measure for Probabilistic 2003 DAGM   inproceedings PDF  
Abstract: The contour of a planar shape is essentially one-dimensional signal embedded in 2-D space; thus the orthogonal distance, which only considers 1-D (norm) deviation from suggested models, is not rich enoughto characterize the description quality of arbitrary model/shape pairs.This paper suggests a generalized distance measure, called Transport Distance, for probabilistic shape modeling. B-Spline primitives are used to represent models. The probability of a hypothetical model for a shape is determined on the basis of the new distance measure. Experiments show that an optimization procedure, which maximize the model probability, generates robust and visually pleasing geometric models for data.
BibTeX:
@inproceedings{Chen2003,
  author = {Wei-Jun Chen and Joachim M. Buhmann},
  title = {A New Distance Measure for Probabilistic},
  booktitle = {DAGM},
  publisher = {DAGM},
  year = {2003},
  volume = {LNCS 2781},
  pages = {507-514}
}
Fischer, B. & Buhmann, J. M. Bagging for Path-Based Clustering 2003 IEEE Transactions on Pattern Analysis and Machine Intelligence   article URL PDF  
Abstract: A resampling scheme for clustering with similarity to bootstrap aggregation (bagging) is presented. Bagging is used to improve the quality of path-based clustering, a data clustering method that can extract elongated structures from data in a noise robust way. The results of an agglomerative optimization method are influenced by small fluctuations of the input data. To increase the reliability of clustering solutions a stochastic resampling method is developed to infer consensus clusters. A related reliability measure allows us to estimate the number of clusters, based on the stability of an optimized cluster solution under resampling. The quality of path-based clustering with resampling is evaluated on a large image dataset of human segmentations.
BibTeX:
@article{fischer.buhmann:bagging,
  author = {Bernd Fischer and Joachim M. Buhmann},
  title = {Bagging for Path-Based Clustering},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2003},
  volume = {25},
  number = {11},
  pages = {1411-1415},
  url = {http://dx.doi.org/10.1109/TPAMI.2003.1240115}
}
Fischer, B. & Buhmann, J. M. Path-Based Clustering for Grouping Smooth Curves and Texture Segmentation 2003 IEEE Transactions on Pattern Analysis and Machine Intelligence   article URL PDF  
Abstract: Perceptual Grouping organizes image parts in clusters based on psychophysically plausible similarity measures. We propose a novel grouping method in this paper which stresses connectedness of image elements via mediating elements rather than favoring high mutual similarity. This grouping principle yields superior clustering results when objects are distributed on low-dimensional extended manifolds in a feature space and not as local point clouds. In addition to extracting connected structures, objects are singled out as outliers when they are too far away from any cluster structure. The objective function for this perceptual organization principle is optimized by a fast agglomerative algorithm. We report on perceptual organization experiments where small edge elements are grouped to smooth curves. The generality of the method is emphasized by results from grouping textured images with texture gradients in an unsupervised fashion.
BibTeX:
@article{fischer.buhmann:path-based,
  author = {Bernd Fischer and Joachim M. Buhmann},
  title = {Path-Based Clustering for Grouping Smooth Curves and Texture Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2003},
  volume = {25},
  number = {4},
  pages = {513-518},
  url = {http://dx.doi.org/10.1109/TPAMI.2003.1190577}
}
Hermes, L. & Buhmann, J. A Minimum Entropy Approach to Adaptive Image Polygonization 2003 IEEE Transaction on Image Processing   inproceedings PDF  
Abstract: This paper introduces a novel adaptive image segmentationalgorithm which represents images by polygonal segments.The algorithm is based on an intuitive generative modelfor pixel intensities and its associated cost function which can be effectively optimized by a hierarchical triangulation algorithm. A triangular mesh is iteratively refined and reorganized to extract a compact description of the essential image structure. After analyzingfundamental convexity properties of our cost function, weadapt an information-theoretic bound to assess the statistical significance of a given triangulation step. The bound effectively defines a stopping criterion to limit the number of triangles in the mesh, thereby avoiding undesirable overfitting phenomena. It alsofacilitates the development of a multiscale variant of the triangulation algorithm, which substantially improves its computational demands. The algorithm has various applications in contextual classification, remote sensing, and visual object recognition. It is particularly suitable for the segmentation of noisy imagery.
BibTeX:
@inproceedings{Hermes2003,
  author = {Lothar Hermes and Joachim Buhmann},
  title = {A Minimum Entropy Approach to Adaptive Image Polygonization},
  booktitle = {IEEE Transaction on Image Processing},
  publisher = {IEEE},
  year = {2003},
  volume = {12}
}
Hermes, L. & Buhmann, J. M. Semi-Supervised Image Segmentation by Parametric Distributional Clustering 2003 Energy Minimization Methods in Computer Vision and Pattern Recognition   inproceedings PDF  
Abstract: The problem of semi-supervised image segmentation is fre-quently posed e.g. in remote sensing applications. In this setting, one aims at finding a decomposition of a given image into its constituent regions, which are typically assumed to have homogeneously distributed pixel values. In addition, it is requested that these regions can be equipped with some semantics, i.e. that they can be matched to particular land cover classes. For this purpose, class labels are provided for a small sub-set of the image data. The demand that the image segmentation re-spects those class labels implies that the segmentation algorithm should be posed as a constrained optimization problem.We extend the Parametric Distributional Clustering (PDC) algorithm to fit into this learning framework. The resulting optimization problem is solved by constrained Deterministic Annealing. The approach is illus-trated for both artificial data and real-world synthetic aperture radar (SAR) imagery.
BibTeX:
@inproceedings{Hermes2003a,
  author = {Lothar Hermes and Joachim M. Buhmann},
  title = {Semi-Supervised Image Segmentation by Parametric Distributional Clustering},
  booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition},
  publisher = {CVPR},
  year = {2003},
  pages = {229-245}
}
Ommer, B. & Buhmann, J. M. A Compositionality Architecture for Perceptual Feature Grouping 2003 Energy Minimization Methods in Computer Vision and Pattern Recognition   inproceedings PDF  
Abstract: We propose a compositionality architecture for perceptual organization which establishes a novel, generic, algorithmic framework for feature binding and condensation of semantic information in im-ages. The underlying algorithmic ideas require a hierarchical structure for various types of objects and their groupings, which are guided by gestalt laws from psychology. A rich set of predefined feature detectors with uncertainty that perform real-valued measurements of relationships between objects can be combined in this exible Bayesian framework. Compositions are inferred by minimizing the negative posterior group-ing probability. The model structure is founded on the fundamental per-ceptual law of Prägnanz. The grouping algorithm performs hierarchical agglomerative clustering and it is rendered computationally feasible by visual pop-out. Evaluation on the edgel grouping task confirms the ro-bustness of the architecture and its applicability to grouping in various visual scenarios.
BibTeX:
@inproceedings{Ommer2003,
  author = {Bj\"orn Ommer and Joachim M. Buhmann},
  title = {A Compositionality Architecture for Perceptual Feature Grouping},
  booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition},
  publisher = {CVPR},
  year = {2003},
  volume = {LNCS 2683},
  pages = {275-290}
}
Roth, V., Laub, J., Buhmann, J. M. & Müller, K.-R. Going Metric: Denoising Pairwise Data 2003 Advances in Neutral Information Processing Systems   inproceedings PDF  
Abstract: Pairwise data in empirical sciences typically violate metricity, either due to noise or due to fallible estimates, and therefore are hard to analyze by conventional machine learning technology. In this paper we therefore stduy ways to work around this problem. First, we present an alternative embedding to multi-dimensional scaling (MDS) that allows us to apply a variety of classical machine learning and signal processing algorithms. The class of pairwise grouping algorithms which share the shift-invariance property is statistically invariant under this embedding procedure. leading to identical assignments of objects to clusters. Based on this new vestorial representation, denoising methods are applied in a second step. Both steps provide a theoretically well controlled setup to translate from pairwise data to the respective denoised metric representation. We demonstrate the practical usefulness of our theoretical reasoning by discovering structure in protein sequence data bases, visibly improving performance upon existing automatic methods.
BibTeX:
@inproceedings{Roth2003,
  author = {Volker Roth and Julian Laub and Joachim M. Buhmann and Klaus-Robert M\"uller},
  title = {Going Metric: Denoising Pairwise Data},
  booktitle = {Advances in Neutral Information Processing Systems},
  publisher = {NIPS},
  year = {2003},
  volume = {15},
  pages = {817-824}
}
Roth, V., Laub, J., Kawanabe, M. & Buhmann, J. M. Optimal Cluster Preserving Embedding of Nonmetric Proximity Data 2003 IEEE Transactions on Pattern Analysis and Machine Intelligence   article PDF  
Abstract: For several major applications of data analysis, objects are often not represented as feature vectors in a vector space, but rather by a matrix gathering pairwise proximities. Such pairwise data often violates metricity and, therefore, cannot be naturally embedded in a vector space. Concerning the problem of unsupervised structure detection or clustering, in this paper, a new embedding method for pairwise data into Euclidean vector spaces is introduced. We show that all clustering methods, which areinvariant under additive shifts of the pairwise proximities, can be reformulated as grouping problems in Euclidian spaces. The most prominent property of this constant shift embedding framework is the complete preservation of the cluster structure in the embeddingspace. Restating pairwise clustering problems in vector spaces has several important consequences, such as the statistical description of the clusters by way of cluster prototypes, the generic extension of the grouping procedure to a discriminative prediction rule, and theapplicability of standard preprocessing methods like denoising or dimensionality reduction.
BibTeX:
@article{Roth2003a,
  author = {Volker Roth and Julian Laub and Motoaki Kawanabe and Joachim M. Buhmann},
  title = {Optimal Cluster Preserving Embedding of Nonmetric Proximity Data},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2003},
  volume = {25},
  number = {12}
}
Braun, M. L. & Buhmann, J. M. The Noisy Euclidean Traveling Salesman Problem and Learning 2002 NIPS   inproceedings PDF  
Abstract: We consider noisy Euclidean traveling salesman problems in the plane, which are random combinatorial problems with underlying structure. Gibbs sampling is used to compute average trajectories, which estimate the underlying structure common to all instances. This procedure requires identifying the exact relationship between permutations and tours. In a learning setting, the average trajectory is used as a model to construct solutions to new instances sampledfrom the same source. Experimental results show that the average trajectory can in fact estimate the underlying structure and that overfitting effects occur if the trajectory adapts too closely to a single instance.
BibTeX:
@inproceedings{Braun2002,
  author = {Mikio L. Braun and Joachim M. Buhmann},
  title = {The Noisy Euclidean Traveling Salesman Problem and Learning},
  booktitle = {NIPS},
  publisher = {NIPS},
  year = {2002},
  volume = {14}
}
Buhmann, J. M. Data Clustering and Learning 2002 Handbook of Brain Theory and Neural Networks   inbook PDF  
Abstract: Intelligent data analysis extracts symbolic information and relations between objects from quantitative or qualitative data. A prominent class of methods are clustering or grouping principles which are designed to discover and extract structures hidden in data sets. The parameters which represent the clusters are either estimated on the basis of quality criteria or cost functions or, alternatively, they are derived by local search algorithms which are not necessarily following the gradient of a global quality criterion. This approach to inference of structure in data is known as unsupervised learning in the neural computation literature. Clustering as a fundamental pattern recognition problem can be characterized by the following design steps:1) Data Representation: What data types represent the objects in the best way to stress relations between the objects, e.g., similarity? 2) Modeling: How can we formally characterize interesting and relevant cluster structures in data sets? 3) Optimization: How can we e ciently search for cluster structures? 4) Validation: How can we validate selected or learned structures?It is important to note that the data representation issue predetermines what kind of cluster structures can be discovered in the data. Vectorial data, proximity or similarity data and histogram data are three examples of a wide variety of data types which are analyzed in the clustering literature. On the basis of the data representation, the modeling of clusters de nes the notion of groups of clusters in the data and separates desired group structures from unfavorable ones. We consider it mandatory that the modeling step yields a quality measure which is either optimized or approximated during the search for hidden structure in data sets. Formulating the search for clusters as an optimization problem allows us to validate clustering results by large deviation estimates, i.e., robust cluster structures in data should vary little from one data set to a second data set generated by the same data source.
BibTeX:
@inbook{Buhmann2002,
  author = {Joachim M. Buhmann},
  title = {Data Clustering and Learning},
  booktitle = {Handbook of Brain Theory and Neural Networks},
  publisher = {MIT Press},
  year = {2002},
  pages = {333-333},
  edition = {2nd}
}
Fischer, B. & Buhmann, J. M. Data Resampling for Path Based Clustering 2002 Pattern Recognition - Symposium of the DAGM 2002   inproceedings URL PDF  
Abstract: Path Based Clustering assigns two objects to the same cluster if they are connected by a path with high similarity between adjacent objects on the path. In this paper, we propose a fast agglomerative algorithm to minimize the Path Based Clustering cost function. To enhance the reliability of the clustering results a stochastic resampling method is used to generate candidate solutions which are merged to yield empirical assignment probabilities of objects to clusters. The resampling algorithm measures the reliability of the clustering solution and, based on their stability, determines the number of clusters.
BibTeX:
@inproceedings{fischer.buhmann:data,
  author = {Bernd Fischer and Joachim M. Buhmann},
  title = {Data Resampling for Path Based Clustering},
  booktitle = {Pattern Recognition - Symposium of the DAGM 2002},
  year = {2002},
  volume = {LNCS 2449},
  pages = {206 - 214},
  url = {http://www.springerlink.com/content/pubpn9pgcbmrgtxc/}
}
Hermes, L., Zöller, T. & Buhmann, J. M. Parametric Distributional Clustering for Image Segmentation 2002 Computer Vision - ECCV 2002   inproceedings PDF  
Abstract: Unsupervised Image Segmentation is one of the central issues in Computer Vision. From the viewpoint of exploratory data analysis, segmentation can be formulated as a clustering problem in which pixels or small image patches are grouped together based on local feature information. In this contribution, parametrical distributional clustering (PDC) is presented as a novel approach to image segmentation. In contrast to noise sensitive point measurements, local distributions of image features provide a statistically robust description of the local image properties. The segmentation technique is formulated as a generative model in the maximum likelihood framework. Moreover, there exists an insightful connection to the novel information theoretic concept of the Information Bottleneck (Tishby et al., 1999), which emphasizes the compromise between efficient coding of an image and preservation of characteristic information in the measured feature distributions.The search for good grouping solutions is posed as an optimization problem, which is solved by deterministic annealing techniques. In order to further increase the computational efficiency of the resulting segmentation algorithm, a multi-scale optimization scheme is developed. Finally, the performance of the novel model is demonstrated by segmentation of color images from the Corel data base.
BibTeX:
@inproceedings{Hermes2002,
  author = {Lothar Hermes and Thomas Z\"oller and Joachim M. Buhmann},
  title = {Parametric Distributional Clustering for Image Segmentation},
  booktitle = {Computer Vision - ECCV 2002},
  publisher = {A. Heyden, G. Sparr, M. Nielsen, P. Johansen},
  year = {2002},
  volume = {3},
  pages = {577-591}
}
Lange, T., Braun, M., Roth, V. & Buhmann, J. Stability-Based Model Selection 2002 NIPS   inproceedings PDF  
Abstract: Model selection is linked to model assessment, which is the problem of comparing different models, or model parameters, for a specific learning task. For supervised learning, the standard practical technique is cross-validation, which is not applicable for semi-supervised and unsupervised settings. In this paper, a new model assessment scheme is introduced which is based on a notion of stability. The stability measure yields an upper bound to cross-validation in the supervised case, but extends to semi-supervised and unsupervised problems. In the experimental part, the performance of the stability measure is studied for model order selection in comparison to standard techniques in this area.
BibTeX:
@inproceedings{Lange2002,
  author = {Tilman Lange and Mikio Braun and Volker Roth and Joachim Buhmann},
  title = {Stability-Based Model Selection},
  booktitle = {NIPS },
  publisher = {NIPS },
  year = {2002}
}
Marx, Z., Dagan, I., Buhmann, J. M. & Shamir, E. Coupled Clustering: A Method for Detecting Structural Correspondence 2002 Journal of Machine Learning Research   article PDF  
Abstract: This paper proposes a new paradigm and a computational framework for revealing equivalencies (analogies) between sub-structures of distinct composite systems that are initially represented by unstructured data sets. For this purpose, we introduce and investigate a variant of traditional data clustering, termed coupled clustering, which outputs a configuration of corresponding subsets of two such representative sets. We apply our method to synthetic as well as textual data. Its achievements in detecting topical correspondences between textual corpora are evaluated through comparison to performance of human experts.
BibTeX:
@article{Marx2002,
  author = {Zvika Marx and Ido Dagan and Joachim M. Buhmann and Eli Shamir},
  title = {Coupled Clustering: A Method for Detecting Structural Correspondence},
  journal = {Journal of Machine Learning Research},
  year = {2002},
  volume = {3},
  pages = {747-780}
}
Roth, V., Lange, T., Braun, M. & Buhmann, J. A Resampling Approach to Cluster Validation 2002 15th Symposium Held in Berlin , Germany 2002 (COMPSTAT2002)   inproceedings PDF  
Abstract: The concept of cluster stability is introduced as a means for assessing the validity of data partitionings found by clustering algorithms. It allows us to explicitly quantify the quality of a clustering solution, without being dependent on external information. The principle of maximizing the cluster stability can be interpreted as choosing the most self-consistent data partitioning. We present an empirical estimator for the theoretically derived stability index, based on imitating independent sample-sets by way of resampling. Experiments on both toy-examples and real-world problems effectively demonstrate that the proposed validation principle is highly suited for model selection.
BibTeX:
@inproceedings{Roth2002,
  author = {Volker Roth and Tilman Lange and Mikio Braun and Joachim Buhmann},
  title = {A Resampling Approach to Cluster Validation},
  booktitle = {15th Symposium Held in Berlin , Germany 2002 (COMPSTAT2002)},
  year = {2002},
  pages = {123-128}
}
Roth, V., Braun, M., Lange, T. & Buhmann, J. M. Stability-Based Model Order Selection in Clustering with Applications to Gene Expression Data 2002 Artificial Neural Networks - ICANN 2002   inproceedings PDF  
Abstract: The concept of cluster stability is introduced as a means for assessing the validity of data partitionings found by clustering algorithms. It allows us to explicitly quantify the quality of a clustering solution, without being dependent on external information. The principle of maximizing the cluster stability can be interpreted as choosing the most self-consistent data partitioning. We present an empirical estimator for the theoretically derived stability index, based on resampling. Experiments are conducted on well known gene expression data sets, re-analyzing the work by Alon et al. [1] and by Spellman et al. [2].
BibTeX:
@inproceedings{Roth2002a,
  author = {Volker Roth and Mikio Braun and Tilman Lange and Joachim M. Buhmann},
  title = {Stability-Based Model Order Selection in Clustering with Applications to Gene Expression Data},
  booktitle = {Artificial Neural Networks - ICANN 2002},
  year = {2002},
  volume = {LNCS 2415}
}
Zöller, T., Hermes, L. & Buhmann, J. M. Combined Color and Texture Segmentation by Parametric Distributional Clustering 2002 ICPR '02   inproceedings PDF  
Abstract: Unsupervised image segmentation can be formulated as a clustering problem in which pixels or small image patches are grouped together based on local feature information. In this contribution, parametric distributional clustering (PDC) is presented as a novel approach to image segmentation based on color and texture clues. The objective function of the PDC model is derived from the recently proposed Information Bottleneck framework (Tishby et al. [8]), but it can equivalently be formulated in terms of a maximum likelihood solution. Its optimization is performed by determin-istic annealing. Segmentation results are shown for natural wildlife imagery.
BibTeX:
@inproceedings{Zoller2002,
  author = {Thomas Z\"oller and Lothar Hermes and Joachim M. Buhmann},
  title = {Combined Color and Texture Segmentation by Parametric Distributional Clustering},
  booktitle = {ICPR '02},
  year = {2002},
  volume = {2},
  pages = {627-630}
}
Zöller, T. & Buhmann, J. M. Self-organized Clustering of Mixture Models for Combined Color and Texture Segmentation 2002 The 2nd international workshop on texture analysis and segmentation   inproceedings PDF  
Abstract: The segmentation of images based on color and texture cues is formulated as a clustering problem in the joint color and texture space. Small image patches are grouped together on the basis of local color and spatial frequency statistics which is captured by Gaussian mixture models in feature space. The locality of segments in feature space is taken into account by the topological organization of the cluster structure which corresponds to self-organizing maps. The clusters define a one dimensional chain in the space of mixture models, which favors an ordering of the groups with similar color and texture distributions. The probabilistic model is tested by segmentation experiments on images from the Corel data base.
BibTeX:
@inproceedings{Zoller2002a,
  author = {Thomas Z\"oller and Joachim M. Buhmann},
  title = {Self-organized Clustering of Mixture Models for Combined Color and Texture Segmentation},
  booktitle = {The 2nd international workshop on texture analysis and segmentation},
  year = {2002},
  pages = {163-167}
}
Buhmann, J. M. Clustering Principles and Empirical Risk Approximation 2001 International Conference on Applied Statistical Models for Data Analysis (ASMDA'01)   inproceedings PDF  
Abstract: Data Clustering is one of the fundamental techniques in pattern recognition to extract structure from data. We discuss a maximum entropy approach to clustering for different clustering cost functions and relate it to the estimation principle of Empirical Risk Approximation. Large deviation techniques from statistical learning theory provide guarantees for the stability of clustering solutions.
BibTeX:
@inproceedings{Buhmann2001,
  author = {Joachim M. Buhmann},
  title = {Clustering Principles and Empirical Risk Approximation},
  booktitle = {International Conference on Applied Statistical Models for Data Analysis (ASMDA'01)},
  year = {2001}
}
Fischer, B., Zöller, T. & Buhmann, J. M. Path Based Pairwise Data Clustering with Application to Texture Segmentation 2001 Energy Minimization Methods in Computer Vision and Pattern Recognition   inproceedings URL PDF  
Abstract: Most cost function based clustering or partitioning methods measure the compactness of groups of data. In contrast to this picture of a point source in feature space, some data sources are spread out on a low-dimensional manifold which is embedded in a high dimensional data space. This property is adequately captured by the criterion of connectedness which is approximated by graph theoretic partitioning methods. We propose in this paper a pairwise clustering cost function with a novel dissimilarity measure emphasizing connectedness in feature space rather than compactness. The connectedness criterion considers two objects as similar if there exists a mediating intra cluster path without an edge with large cost. The cost function is optimized in a multi-scale fashion. This new path based clustering concept is applied to segment textured images with strong texture gradients based on dissimilarities between image patches.
BibTeX:
@inproceedings{fischer.zoller.ea:path,
  author = {Bernd Fischer and Thomas Z\"oller and Joachim M. Buhmann},
  title = {Path Based Pairwise Data Clustering with Application to Texture Segmentation},
  booktitle = {Energy Minimization Methods in Computer Vision and Pattern Recognition},
  year = {2001},
  volume = {LNCS 2134},
  pages = {235-250},
  url = {http://www.springerlink.com/content/a71hve79rpm83jrn/}
}
Hermes, L. & Buhmann, J. M. A New Adaptive Algorithm for the Polygonization of Noisy Imagery 2001   techreport PDF  
Abstract: This report introduces a novel adaptive image segmentation algorithm which represents images by polygonal segments and which is particularly suitable for the segmentation of noisy imagery. At first we suggest an intuitive generative model and its associated cost function. The cost function can effectively be optimized by a hierarchical triangulation algorithm, which iteratively refines and reorganizes a triangular mesh and finally provides a compact description of the essential image structure. After analyzing fundamental properties of our cost function, we adapt an information-theoretic bound to assess the statistical significance of a given triangulation step. The bound effectively defines a stopping criterion to limit the number of triangles in the mesh, thereby avoiding undesirable overfitting phenomena. Besides, it facilitates the development of a multi-scale variant of the triangulation algorithm, which substantially decreases its computational demands. The algorithm has various important applications in contextual classification, remote sensing, and visual object recognition.
BibTeX:
@techreport{Hermes2001,
  author = {Lothar Hermes and Joachim M. Buhmann},
  title = {A New Adaptive Algorithm for the Polygonization of Noisy Imagery},
  year = {2001},
  number = {IAI-TR-2001-3}
}
Hermes, L. & Buhmann, J. M. Contextual Classification by Entropy-Based Polygonization 2001 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'01)   inproceedings PDF  
Abstract: To improve the performance of pixel-wise classification results for remotely sensed imagery, several contextual classification schemes have been proposed that aim at avoiding classification noise by local averaging. These algorithms, however, bear the serious disadvantage of smoothing the segment boundaries and producing rounded segments that hardly match the true shapes. In this contribution, we present a novel contextual classification algorithm that overcomes these shortcomings. Using a hierarchical approach for generating a triangular mesh, it decomposes the image into a set of polygons that, in our application, represent individual land-cover types. Compared to classical contextual classification approaches, this method has the advantage of generating output that matches the intuitively expected type of segmentation. Besides, it achieves excellent classification results.
BibTeX:
@inproceedings{Hermes2001a,
  author = {Lothar Hermes and Joachim M. Buhmann},
  title = {Contextual Classification by Entropy-Based Polygonization},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'01)},
  year = {2001},
  volume = {2},
  pages = {442-447}
}
Marx, Z., Dagan, I. & Buhmann, J. M. Coupled Clustering: A Method for Detecting Structural Correspondence 2001 18th International Conference on Machine Learning (ICML 2001)   inproceedings PDF  
Abstract: This paper proposes a new paradigm and a computational framework for revealing equivalencies (analogies) between sub-structures of distinct composite systems that are initially represented by unstructured data sets. For this purpose, we introduce and investigate a variant of traditional data clustering, termed coupled clustering, which outputs a configuration of corresponding subsets of two such representative sets. We apply our method to synthetic as well as textual data. Its achievements in detecting topical correspondences between textual corpora are evaluated through comparison to performance of human experts.
BibTeX:
@inproceedings{Marx2001,
  author = {Zvika Marx and Ido Dagan and Joachim M. Buhmann},
  title = {Coupled Clustering: A Method for Detecting Structural Correspondence},
  booktitle = {18th International Conference on Machine Learning (ICML 2001)},
  year = {2001},
  pages = {353-360}
}
Roth, V. & Tsuda, K. Pairwise Coupling for Machine Recognition of Hand-Printed Japanese Characters 2001 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'01)   inproceedings PDF  
Abstract: Machine recognition of hand-printed Japanese characters has been an area of great interest for many years. The major problem with this classification task is the huge number of different characters. Applying standard state-of-the-art techniques, such as the SVM, to multi-class problems of this kind imposes severe problems, both of a conceptual and a technical nature: (i) separating one class from all others may be an unnecessarily hard problem; (ii) solving these subproblems can impose unacceptably high computational costs. In this paper, a new approach to Japanese character recognition is presented that successfully overcomes these shortcomings. It is based on a pairwise coupling procedure for probabilistic two-class kernel classifiers. Experimental results for Hiragana recognition effectively demonstrate that our method attains an excellent level of prediction accuracy while imposing very low computational costs.
BibTeX:
@inproceedings{Roth2001,
  author = {Volker Roth and Koji Tsuda},
  title = {Pairwise Coupling for Machine Recognition of Hand-Printed Japanese Characters},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR'01)},
  year = {2001},
  volume = {1},
  pages = {1120-1125}
}
Roth, V. Probabilistic Discriminative Kernel Classifiers for Multiclass Problems 2001 Pattern Recognition--DAGM'01   inproceedings PDF  
Abstract: Logistic regression is presumably the most popular representative of probabilistic discriminative classifiers. In this paper, a kernel variant of logistic regression is introduced as an iteratively re-weighted least-squares algorithm in kernel-induced feature spaces. This formulation allows us to apply highly efficient approximation methods that are capable of dealing with large-scale problems. For multi-class problems, a pairwise coupling procedure is proposed. Pairwise coupling for kernelized logistic regression effectively overcomes conceptual and numerical problems of standard multi-class kernel classifiers.
BibTeX:
@inproceedings{Roth2001a,
  author = {Volker Roth},
  title = {Probabilistic Discriminative Kernel Classifiers for Multiclass Problems},
  booktitle = {Pattern Recognition--DAGM'01},
  year = {2001},
  volume = {LNCS 2191},
  pages = {246-253}
}
Roth, V. Sparse Kernel Regressors 2001 Artificial Neural Networks--ICANN 2001   inproceedings PDF  
Abstract: Sparse kernel regressors have become popular by applying the support vector method to regression problems. Although this approach has been shown to exhibit excellent generalization properties in many experiments, it suffers from several drawbacks: the absence of probabilistic outputs, the restriction to Mercer kernels, and the steep growth of the number of support vectors with increasing size of the training set. In this paper we present a new class of kernel regressors that effectively overcome the above problems. We call this new approach generalized LASSO regression. It has a clear probabilistic interpretation, produces extremely sparse solutions, can handle learning sets that are corrupted by outliers, and is capable of dealing with large-scale problems.
BibTeX:
@inproceedings{Roth2001b,
  author = {Volker Roth},
  title = {Sparse Kernel Regressors},
  booktitle = {Artificial Neural Networks--ICANN 2001},
  year = {2001},
  volume = {LNCS 2130},
  pages = {339-346}
}
Rubner, Y., Puzicha, J., Tomasi, C. & Buhmann, J. M. Empirical Evaluation of Dissimilarity Measures for Color and Texture 2001 Computer Vision and Image Understanding   article  
BibTeX:
@article{Rubner2001,
  author = {Yossi Rubner and Jan Puzicha and Carlo Tomasi and Joachim M. Buhmann},
  title = {Empirical Evaluation of Dissimilarity Measures for Color and Texture},
  journal = {Computer Vision and Image Understanding},
  year = {2001},
  volume = {84},
  pages = {25-43}
}
Stenger, B., Ramesh, V., Paragios, N., F.Coetzee & Buhmann, J. M. Topology Free Hidden Markov Models: Application to Background Modeling 2001 Proceedings International Conference on Computer Vision (ICCV 2001)   inproceedings PDF  
Abstract: Hidden Markov Models (HMMs) are increasingly being used in computer vision for applications such as: gesture analysis, action recognition from video, and illumination modeling. Their use involves an off-line learning step that is used as a basis for on-line decision making (i.e. a stationarity assumption on the model parameters). But, real-world applications are often non-stationary in nature. This leads to the need for a dynamic mechanism to learn and update the model topology as well as its parameters. This paper presents a new framework for HMM topology and parameter estimation in an online, dynamic fashion. The topology and parameter estimation is posed as a model selection problem with an MDL prior. Online modifications to the topology are made possible by incorporating a state splitting criterion. To demonstrate the potential of the algorithm, the background modeling problem is considered. Theoretical validation and real experiments are presented.
BibTeX:
@inproceedings{Stenger2001,
  author = {B. Stenger and V. Ramesh and N. Paragios and F.Coetzee and J. M. Buhmann},
  title = {Topology Free Hidden Markov Models: Application to Background Modeling},
  booktitle = {Proceedings International Conference on Computer Vision (ICCV 2001)},
  year = {2001},
  volume = {I},
  pages = {294-301}
}
Suing, M., Hermes, L. & Buhmann, J. M. A New Contour-based Approach to Object Recognition for Assembly Line Robots 2001 Pattern Recognition - 23rd DAGM Symposium   inproceedings PDF  
Abstract: A complete processing chain for visual object recognition is described in this paper. The system automatically detects individual objects on an assembly line, identifies their type, position, and orientation, and, thereby, forms the basis for automated object recognition and manipulation by single-arm robots. Two new ideas entered into the design of the recognition system. First we introduce a new fast and robust image segmentation algorithm that identifies objects in an unsupervised manner and describes them by a set of closed polygonal lines. Second we describe how to embed this object description into an object recognition process that classifies the objects by matching them to a given set of prototypes. Furthermore, the matching function allows us to determine the relative orientation and position of an object. Experimental results for a representative set of real-world tools demonstrate the quality and the practical applicability of our approach.
BibTeX:
@inproceedings{Suing2001,
  author = {Markus Suing and Lothar Hermes and and Joachim M. Buhmann},
  title = {A New Contour-based Approach to Object Recognition for Assembly Line Robots},
  booktitle = {Pattern Recognition - 23rd DAGM Symposium},
  year = {2001},
  volume = {LNCS 2191},
  pages = {329-336}
}
Bengio, Y., Buhmann, J. M., Embrechts, M. & Zurada, J. Introduction to the Special Issue on Neural Networks for Data Mining and Knowledge Discovery 2000 IEEE Transactions on Neural Networks   article  
BibTeX:
@article{Bengio2000,
  author = {Yoshua Bengio and Joachim M. Buhmann and Mark Embrechts and Jacek Zurada},
  title = {Introduction to the Special Issue on Neural Networks for Data Mining and Knowledge Discovery},
  journal = {IEEE Transactions on Neural Networks},
  year = {2000},
  volume = {11},
  number = {3},
  pages = {545-549}
}
Buhmann, J. M. & Held, M. Model selection in clustering by uniform convergence bounds 2000 Advances in Neural Information Processing Systems 12   inproceedings  
Abstract: Unsupervised learning algorithms are designed to extract structure from data samples. Reliable and robust inference requires a guarantee that extracted structures are typical for the data source, i.e., similar structures have to be infered from a second sample set of the same data source. The overfitting phenomenon in maximum entropy based annealing algorithms is exemplarily studied for a class of histogram clustering models. Bernstein's inequality for large deviations is used to determine the maximally achievable approximation quality parameterized by a minimal temperature. Monte Carlo simulations support the proposed model selection criterion by finite temperature annealing.
BibTeX:
@inproceedings{Buhmann2000,
  author = {Joachim M. Buhmann and Marcus Held},
  title = {Model selection in clustering by uniform convergence bounds},
  booktitle = {Advances in Neural Information Processing Systems 12},
  year = {2000},
  pages = {216-222}
}
Hermes, L. & Buhmann, J. M. Feature Selection for Support Vector Machines 2000 International Conference on Pattern Recognition (ICPR'00)   inproceedings PDF  
Abstract: In the context of support vector machines (SVM), high dimensional input vectors often reduce the computational efficiency and significantly slow down the classification process. In this paper, we propose a strategy to rank individual components according to their influence on the class assignments. This ranking is used to select an appropriate subset of the features. It replaces the original feature set without significant loss in classification accuracy. Often, the generalization ability of the classifier even increases due to the implicit regularization achieved by feature pruning.
BibTeX:
@inproceedings{Hermes2000,
  author = {Lothar Hermes and Joachim M. Buhmann},
  title = {Feature Selection for Support Vector Machines},
  booktitle = {International Conference on Pattern Recognition (ICPR'00)},
  year = {2000},
  volume = {2},
  pages = {716-719}
}
Klock, H. & Buhmann, J. M. Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach 2000 Pattern Recognition   article  
BibTeX:
@article{Klock2000,
  author = {Hansj\"org Klock and Joachim M. Buhmann},
  title = {Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach},
  journal = {Pattern Recognition},
  year = {2000},
  volume = {33},
  number = {4},
  pages = {651-669}
}
Puzicha, J., Held, M., Ketterer, J., Buhmann, J. M. & Fellner, D. On Spatial Quantization of Color Images 2000 IEEE Transactions in Image Processing   article PDF  
Abstract: Image quantization and digital halftoning are fundamental image processing problems in computer vision and graphics. Both steps are generally performed sequentially and, in most cases, independent of each other. Color reduction with a pixel-wise defined distortion measure and the halftoning process with its local averaging neighborhood typically optimize different quality criteria or, frequently, follow a heuristic approach without reference to any quality measure. In this paper we propose a new model to simultaneously quantize and halftone color images. The method is based on a rigorous cost-function approach which optimizes a quality criterion derived from a simplified model of human perception. It incorporates spatial and contextual information into the quantization and thus overcomes the artificial separation of quantization and halftoning. Optimization is performed by an efficient multiscale procedure which substantially alleviates the computational burden. The quality criterion and the optimization algorithms are evaluated on a representative set of artificial and real-world images showing a significant image quality improvement compared to standard color reduction approaches. Applying the developed cost function we also suggest a new distortion measure for evaluating the quality of color reduction schemes.
BibTeX:
@article{Puzicha2000,
  author = {Jan Puzicha and Markus Held and Jens Ketterer and Joachim M. Buhmann and Dieter Fellner},
  title = {On Spatial Quantization of Color Images},
  journal = {IEEE Transactions in Image Processing},
  year = {2000},
  volume = {9},
  number = {4},
  pages = {666-682}
}
Will, S., Hermes, L., Buhmann, J. & Puzicha, J. On Learning Texture Edge Detectors 2000 International Conference on Image Processing (ICIP'00)   inproceedings PDF  
Abstract: Texture is an inherently non-local image property. All common texture descriptors, therefore, have a significant spatial support which renders classical edge detection schemes inadequate for the detection of texture boundaries.In this paper we propose a novel scheme to learn filters for texture edge detection. Textures are defined by the statistical distribution of Gabor filter responses. Optimality criteria for detection reliability and localization accuracy are suggested in the spirit of Canny's edge detector. Texture edges are determined as zero crossings of the difference of the two a posteriori class distributions. An optimization algorithm is designed to determine the best filter kernel according to the underlying quality measure. The effectiveness of the approach is demonstrated on texture mondrians composed from the Brodatz album and a series of synthetic aperture radar (SAR) imagery. Moreover, we indicate how the proposed scheme can be combined with snake-type algorithms for prior-knowledge driven boundary refinement and interactive annotation.
BibTeX:
@inproceedings{Will2000,
  author = {Stefan Will and Lothar Hermes and Joachim Buhmann and Jan Puzicha},
  title = {On Learning Texture Edge Detectors},
  booktitle = {International Conference on Image Processing (ICIP'00)},
  year = {2000},
  pages = {877-880}
}
Zöller, T. & Buhmann, J. M. Active Learning for Hierarchical Pairwise Data Clustering 2000 ICPR'00   inproceedings PDF  
Abstract: Pairwise data clustering is a well founded grouping technique based on relational data of objects which has a widespread application domain. However, its applicability suffers from the disadvantageous fact that N objects give rise to N(N-1)/2 relations. To cure this unfavorable scaling, techniques to sparsely sample the relations have been developed. Yet a randomly chosen subset of the data might not grasp the structure of the complete data set. To overcome this deficit, we use active learning methods from the field of Statistical Decision Theory. Extending on existing approaches we present a novel algorithm for actively learning hierarchical group structures based on mean field annealing optimization.
BibTeX:
@inproceedings{Zoller2000,
  author = {Thomas Z\"oller and Joachim M. Buhmann},
  title = {Active Learning for Hierarchical Pairwise Data Clustering},
  booktitle = {ICPR'00},
  year = {2000},
  volume = {2},
  pages = {186-189}
}
Buhmann, J. M., Malik, J. & Perona, P. Image Recognition: Visual Grouping, Recognition and Learning 1999 National Academy of Science   inproceedings PDF  
Abstract: Vision extract useful information from images. Reconstructing the three-dimensional structure of our environment and recognizing the objects that populate it are among the most important functions of our visual system. Computer vision researchers study the computational principles of vision and aim at designing algorithms that reproduce these functions. Vision is difficult: the same scene may give rise to very different images, depending on illumination and viewpoint. Typically, an astronomical number of hypotheses exist that in principle have to be analyzed to infer a correct scene description. Moreover, image information might be extracted at different levels of spatial and logical resolution dependent on the image processing task. Knowledge of the world allows the visual system to limit the amount of ambiguity and to greatly simplify isual computations. We discuss how simple properties of the world are captured by the Gestalt rules of grouping, how the visual system may learn and organize models of objects for recognition, and how one may control the complexity of the description that the visual system computes.
BibTeX:
@inproceedings{Buhmann1999,
  author = {Joachim M. Buhmann and Jitendra Malik and Pietro Perona},
  title = {Image Recognition: Visual Grouping, Recognition and Learning},
  booktitle = {National Academy of Science},
  year = {1999},
  volume = {96}
}
Buhmann, J. & Held, M. On the optimal number of clusters in histogram clustering 1999 Jahrestagung 99 / Gesellschaft fuer Klassifikation   inproceedings PDF  
Abstract: Unsupervised learning algorithms are designed to extract structure from data samples. The quality of a structure is measured by a cost function which is usually minimized to infer optimal parameters characterizing the hidden structure in the data. Reliable and robust inference requires a guarantee that extracted structures are typical for the data source, i.e., similar structures have to be extracted from a second sample set of the same data source. Lack of robustness is known as overfitting from the statistics and the machine learning literature. In this paper the overfitting phenomenon is characterized for a class of histogram clustering models which play a prominent role in information retrieval, linguistic and computer vision applications. Learning algorithms with robustness to sample fluctuations are derived from large deviation theory and the maximum entropy principle for the learning process. The theory validates continuation methods like simulated or deterministic annealing as robust approximation schemes from a statistical learning theory point of view. It predicts the optimal approximation quality, parameterized by a minimal finite temperature, for given covering numbers of the hypothesis class for structures. Monte Carlo simulations are presented to support the underlying inference principle.
BibTeX:
@inproceedings{Buhmann1999a,
  author = {Joachim Buhmann and Marcus Held},
  title = {On the optimal number of clusters in histogram clustering},
  booktitle = {Jahrestagung 99 / Gesellschaft fuer Klassifikation},
  year = {1999}
}
Held, M., Puzicha, J. & Buhmann, J. Visualizing Group Structure 1999 Advances in Neural Information Processing Systems 11 (NIPS'98)   inproceedings PDF  
Abstract: Cluster analysis is a fundamental principle in exploratory data analysis, providing the user with a description of the group structure of given data. A key problem in this context is the interpretation and visualization of clustering solutions in high-dimensional or abstract data spaces. In particular, fuzzy or probabilistic descriptions of the group structure, essential to capture inter-cluster relations, are hardly assessable by simple inspection of the probabilistic assignment variables. We present a novel approach for the visualization of probabilistic group structure based on a statistical model of the object assignments which have been observed or estimated by a probabilistic clustering procedure. The objects or data points are embedded in a low dimensional Euclidean space by approximating the observed data statistics with a Gaussian mixture model. The algorithm provides a new approach to the visualization of the inherent structure for a broad variety of data types, e.g. histogram data, proximity data and co-occurrence data. To demonstrate the power of the approach, histograms of textured images are visualized as a large-scale data mining application.
BibTeX:
@inproceedings{Held1999,
  author = {Marcus Held and Jan Puzicha and Joachim Buhmann},
  title = {Visualizing Group Structure},
  booktitle = {Advances in Neural Information Processing Systems 11 (NIPS'98)},
  year = {1999}
}
Hermes, L., Frieauff, D., Puzicha, J. & Buhmann, J. M. Support Vector Machines for Land Usage Classification in Landsat TM Imagery 1999 IEEE International Geoscience and Remote Sensing Symposium   inproceedings PDF  
Abstract: Land usage classification is an essential part of many remote sensing applications for mapping, inventory, and yield estimation. In this contribution, we evaluate the potential of the recently introduced support vector machines for remote sensing applications. Moreover, we expand this discriminative technique by a novel Bayesian approach to estimate the confidence of each classification. These estimates are combined with a priori konowledge about topological relations of class labels using a contextual classification step based on the iterative conditional mode algorithm (ICM). As shown for Landsat TM imagery, this strategy is highly competitive and outperforms several commonly used classification schemes.
BibTeX:
@inproceedings{Hermes1999,
  author = {Lothar Hermes and Dieter Frieauff and Jan Puzicha and Joachim M. Buhmann},
  title = {Support Vector Machines for Land Usage Classification in Landsat TM Imagery},
  booktitle = {IEEE International Geoscience and Remote Sensing Symposium},
  year = {1999},
  volume = {1},
  pages = {348-350}
}
Hofmann, T., Puzicha, J. & Jordan, M. Learning from Dyadic Data 1999 Advances in Neural Information Processing Systems 11 (NIPS'98)   inproceedings PDF  
Abstract: Dyadic data refers to a domain with two finite sets of objects in which observations are made for dyads, i.e., pairs with one element from either set. This type of data arises naturally in many application ranging from computational linguistics and information retrieval to preference analysis and computer vision. In this paper we present a systematic, domain-independent framework of learning from dyadic data by statistical mixture models. Our approach covers different models with flat and hierarchical latent class structures. We propose an annealed version of the standard EM algorithm for model fitting which is empirically evaluated on a variety of data sets from different domains.
BibTeX:
@inproceedings{Hofmann1999,
  author = {Thomas Hofmann and Jan Puzicha and Michael Jordan},
  title = {Learning from Dyadic Data},
  booktitle = {Advances in Neural Information Processing Systems 11 (NIPS'98)},
  year = {1999},
  pages = {466-472}
}
Klock, H. & Buhmann, J. M. Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach 1999 Pattern Recognition   article PDF  
Abstract: Multidimensional scaling addresses the problem how proximity data can be faithfully visualized as points in a low-dimensional Euclidian space. The quality of a data embedding is measured by a stress function which compares proximity values with Euclidian distances of the respective points. The corresponding minimization problem is non-convex and sensitive to local minima. We present a novel deterministic annealing algorithm for the frequently used objective SSTRESS and for Sammon mapping, derived in the framework of maximum entropy estimation. Experimental results demonstrate the superiority of our optimization technique compared to conventional gradient descent methods.
BibTeX:
@article{Klock1999,
  author = {Hansj\"org Klock and Joachim M. Buhmann},
  title = {Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach},
  journal = {Pattern Recognition},
  year = {1999},
  volume = {33},
  number = {4},
  pages = {651-669}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. A Theory of Proximity Based Clustering: Structure Detection by Optimization 1999 Pattern Recognition   article PDF  
Abstract: In this paper, a systematic optimization approach for clustering proximity or similarity data is developed. Starting from fundamental invariance and robustness properties, a set of axioms is proposed and discussed to distinguish different cluster compactness and separation criteria. The approach covers the case of sparse proximity matrices, and is extended to nested partitionings for hierarchical data clustering. To solve the associated optimization problems, a rigorous mathematical framework for deterministic annealing and mean-field approximation is presented. Efficient optimization heuristics are derived in a canonical way, which also clarifies the relation to stochastic optimization by Gibbs sampling. Similarity-based clustering techniques have a broad range of possible applications in computer vision, pattern recognition, and data analysis. As a major practical application we present a novel approach to the problem of unsupervised texture segmentation, which relies on statistical tests as a measure of homogeneity. The quality of the algorithms is empirically evaluated on a large collection of Brodatz-like micro-texture Mondrians and on a set of real-word images. To demonstrate the broad usefulness of the theory of proximity based clustering the performances of different criteria and algorithms are compared on an information retrieval task for a document database. The superiority of optimization algorithms for clustering is supported by extensive experiments.
BibTeX:
@article{Puzicha1999,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {A Theory of Proximity Based Clustering: Structure Detection by Optimization},
  journal = {Pattern Recognition},
  year = {1999},
  volume = {33},
  number = {4},
  pages = {617-634}
}
Puzicha, J., Rubner, Y., Tomasi, C. & Buhmann, J. M. Empirical Evaluation of Dissimilarity Measures for Color and Texture 1999 IEEE International Conference on Computer Vision (ICCV'99)   inproceedings PDF  
Abstract: This paper empirically compares nine image disimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Ground truth is collected via a novel random sampling scheme for color, and via an image partitioning method for texture. Quantitative performance evaluations are given for classification, image retrieval and, segmentation tasks, and for a wide variety of dissimilarity measures. It is demonstrated how the selection of a measure, based on large scale evaluation, substantially improves the quality of classification, retrieval , and unsupervised segmentation of color and texturte images.
BibTeX:
@inproceedings{Puzicha1999a,
  author = {Jan Puzicha and Yossi Rubner and Carlo Tomasi and Joachim M. Buhmann},
  title = {Empirical Evaluation of Dissimilarity Measures for Color and Texture},
  booktitle = {IEEE International Conference on Computer Vision (ICCV'99)},
  year = {1999},
  pages = {1165-1173}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. Histogram Clustering for Unsupervised Image Segmentation 1999 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR'99)   inproceedings PDF  
Abstract: This paper introduces a novel statistical mixture model for probabilistic grouping of distributional (histogram) data. Adopting the Bayesian framework, we propose to perform annealed maximum a posteriori estimation to compute optimal clustering solutions. In order to accelerate the optimization process, an efficient multiscale formulation is developed. We present a prototypical application of this method for the unsupervised segmentation of textured images based on local distributions of Gabor coefficients. Benchmark results indicate superior performance compared to K-means clustering and proximity-based algorithms.
BibTeX:
@inproceedings{Puzicha1999b,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {Histogram Clustering for Unsupervised Image Segmentation},
  booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition (CVPR'99)},
  year = {1999},
  pages = {602-608}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. Histogram Clustering for Unsupervised Segmentation and Image Retrieval 1999 Pattern Recognition Letters   article PDF  
Abstract: This paper introduces a novel statistical latent class model for probabilistic grouping of distributional and histogram data. Adopting the Bayesian framework, we propose to perform annealed maximum a posteriori estimation to compute optimal clustering solutions. In order to accelerate the optimization process, an efficient multiscale formulation is developed. We present a prototypical application of this method for unsupervised segmentation of textured images based on local distributions of Gabor coefficients. Benchmark results indicate superior performance compared to K-means clustering and proximity-based algorithms. In a second application the histogram clustering method is utilized to structure image databases for improved image retrieval.
BibTeX:
@article{Puzicha1999c,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {Histogram Clustering for Unsupervised Segmentation and Image Retrieval},
  journal = { Pattern Recognition Letters},
  year = {1999},
  volume = {20},
  pages = {899-909}
}
Puzicha, J. & Buhmann, J. M. Multiscale Annealing for Grouping and Unsupervised texture Segmentation 1999 Computer Vision and Image Understanding (CVIU)   article PDF  
Abstract: We derive real-time global optimization methods for several clustering optimization problems commonly used in unsupervised texture segmentation. Speed is achieved by exploiting the image neighborhood relation of features to design a multiscale optimization technique, while accuracy and global optimization properties are gained using annealing techniques. Coarse grained cost functions are derived for central and histogram-based clustering as well as several sparse proximity-based clustering methods.For optimization deterministic annealing algorithms are applied. Annealing schedule, coarse-to-fine optimization and the estimated number of segments are tightly coupled by a statistical convergence criterion derived from computational learning theory. The notion of optimization scale parametrized by a computational temperature is thus unified with the scales defined by the image resolution and the model or segment complexity.The algorithms are benchmarked on Brodatz-like micro-texture mixtures. Results are presented for an autonomous robotics application. Extensions are discussed in the context of prestructuring large image databases valuable for fast and reliable image retrieval.
BibTeX:
@article{Puzicha1999d,
  author = {Jan Puzicha and Joachim M. Buhmann},
  title = {Multiscale Annealing for Grouping and Unsupervised texture Segmentation},
  journal = {Computer Vision and Image Understanding (CVIU)},
  year = {1999},
  volume = {76},
  number = {3},
  pages = {213-230}
}
Buhmann, J. M., Fellner, D., Held, M., Ketterer, J. & Puzicha, J. Dithered Color Quantization 1998 Computer Craphics Forum   article  
Abstract: Image quantization and digital halftoning are fundamental problems in computer graphics, typically performed when displaying high-color images on non-truecolor devices. Both steps are generally performed sequentially and, in most cases, independent of each other. Color quantization with a pixel-wise defined distortion measure and the dithering process with its local neighborhood typically optimize different quality criteria or, frequently, follow a heuristic without reference to any quality measure. In this paper we propose a new method to simultaneously quantize and dither color images. The method is based on a rigorous cost-function approach which optimizes a quality criterion derived from a generic model of human perception.A highly efficient algorithm for optimization based on a multiscale method is developed for the dithered color quantization cost function. The quality criterion and the optimization algorithms are evaluated on a representative set of artificial and real-world images as well as a collection of icons. A significant image quality improvement is observed compared to standard color reduction approaches.
BibTeX:
@article{Buhmann1998,
  author = {Joachim M. Buhmann and Dieter Fellner and Markus Held and Jens Ketterer and Jan Puzicha},
  title = {Dithered Color Quantization},
  journal = {Computer Craphics Forum},
  year = {1998},
  volume = {17},
  number = {3},
  pages = {219-231}
}
Buhmann, J. M. Empirical Risk Approximation: An Induction Principle for Unsupervised Learning 1998   techreport PDF  
Abstract: Unsupervised learning algorithms are designed to extract structure from data without reference to explicit teacher information. The quality of the infered structure is determined by a quality function which guides the search and validation process of structure in data. This paper proposes EMPIRICAL RISK APPROXIMATION as a new induction principle for unsupervised learning. epsilon-covers are used to coarsen the hypothesis class of possible structures. The complexity of the unsupervised learning models are automatically controlled by large deviation bounds. The maximum entropy principle with deterministic annealing as an efficient search strategy arises from the empirical risk approximation principle as the optimal inference strategy for large learning problems. Parameter selection of learnable data structures is demonstrated for the case of K-means clustering.
BibTeX:
@techreport{Buhmann1998a,
  author = {Joachim M. Buhmann},
  title = {Empirical Risk Approximation: An Induction Principle for Unsupervised Learning},
  year = {1998},
  number = {IAI-TR-98-3}
}
Hofmann, T. & Buhmann, J. M. Competitive Learning Algorithms for Robust Vector Quantization 1998 IEEE Trans. on Signal Processing   article PDF  
Abstract: The efficient representation and encoding of signals with limited resources, e.g., finite storage capacity and restricted transmissionbandwidth, is a fundamental problem in technical as well as biological information processing systems. Typically, under realistic circumstances, the encoding and communication of messages has to deal with different sources of noise and disturbances. In this paper, we propose a unifying approach to data compression by robust vector quantization, which explicitly deals with channel noise, bandwidth limitations, and random elimination of prototypes. The resulting algorithm is able to limit the detrimental effect of noise in a very general communication scenario. In addition, the presented model allows us to derive a novel competitive neural networks algorithm, which covers topology preserving feature maps, the so-called neural-gas algorithm, and the maximum entropy soft-max rule as special cases. Furthermore, continuation methods based on these noise models improve the codebook design by reducing the sensitivity to local minima. We show an exemplary application of the novel robust vector quantization algorithm to image compression for a teleconferencing system.
BibTeX:
@article{Hofmann1998,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Competitive Learning Algorithms for Robust Vector Quantization},
  journal = {IEEE Trans. on Signal Processing},
  year = {1998},
  volume = {46},
  number = {6},
  pages = {1665-1675}
}
Hofmann, T. & Puzicha, J. Mixture Models for Co-occurrence and Histogram Data 1998 International Conference Pattern Recognition   inproceedings PDF  
Abstract: Modeling and predicting co-occurrences of events is a fundamental problem of unsupervised learning. In this contribution, we develop a general statistical framework for analyzing co-occurrence data based on probabilistic clustering by mixture models. More specifically, we discuss three models which pursue different modeling goals and which differ in the way they define the probabilistic partitioning of the observations. Adopting the maximum likelihood principle, annealed EM algorithms are derived for parameter estimation. From the class of potential applications in pattern recognition and data analysis, we have chosen document retrieval, language modeling, and unsupervised texture segmentation to test and evaluate the proposed algorithms.
BibTeX:
@inproceedings{Hofmann1998a,
  author = {Thomas Hofmann and Jan Puzicha},
  title = {Mixture Models for Co-occurrence and Histogram Data},
  booktitle = {International Conference Pattern Recognition},
  year = {1998},
  pages = {192-194}
}
Hofmann, T. & Puzicha, J. Unsupervised Learning from Dyadic Data 1998   techreport PDF  
Abstract: Dyadic data refers to a domain with two finite sets of objects in which observations are made for dyads, i.e., pairs with one element from either set. This includes event co-occurrences, histogram data, and single stimulus preference data as special cases. Dyadic data arises naturally in many applications ranging from computational linguistics and information retrieval to preference analysis and computer vision. In this paper, we present a systematic, domain-independent framework for unsupervised learning from dyadic data by statistical mixture models. Our approach covers different models with flat and hierarchical latent class structures and unifies probabilistic modeling and structure discovery. Mixture models provide both, a parsimonious yet flexible parameterization of probability distributions with good generalization performance on sparse data, as well as structural information about data-inherent grouping structure. We propose an annealed version of the standard Expectation Maximization algorithm for model fitting which is empirically evaluated on a variety of data sets from different domains.
BibTeX:
@techreport{Hofmann1998b,
  author = {Thomas Hofmann and Jan Puzicha},
  title = {Unsupervised Learning from Dyadic Data},
  year = {1998},
  number = {ICSI-TR-98-042}
}
Hofmann, T., Puzicha, J. & Buhmann, J. M. Unsupervised Texture Segmentation in a Deterministic Annealing Framework 1998 IEEE Transactions on Pattern Analysis and Machine Intelligence   article PDF  
Abstract: We present a novel optimization framework for unsupervised texture segmentation that relies on statistical tests as a measure of homogeneity. Texture segmentation is formulated as a data clustering problem based on sparse proximity data. Dissimilarities of pairs of textured regions are computed from a multi-scale Gabor filter image representation. We discuss and compare a class of clustering objective functions which is systematically derived from invariance principles. As a general optimization framework we propose deterministic annealing based on a mean-field approximation. The canonical way to derive clustering algorithms within this framework as well as an efficient implementation of mean-field annealing and the closely related Gibbs sampler are presented. We apply both annealing variants to Brodatz-like micro-texture mixtures and real-word images.
BibTeX:
@article{Hofmann1998c,
  author = {Thomas Hofmann and Jan Puzicha and Joachim M. Buhmann},
  title = {Unsupervised Texture Segmentation in a Deterministic Annealing Framework},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {1998},
  volume = {20},
  number = {8}
}
Hofmann, T. & Puzicha, J. Statistical Models for Co-occurrence Data 1998   techreport  
Abstract: Modeling and predicting co-occurrences of events is a fundamental problem of unsupervised learning. In this contribution we develop a statistical framework for analyzing co-occurrence data in a general setting where elementary observations are joint occurrences of pairs of abstract objects from two finite sets. The main challenge for statistical models in this context is to overcome the inherent data sparseness and to estimate the probabilities for pairs which were rarely observed or even unobserved in a given sample set. Moreover, it is often of considerable interest to extract grouping structure or to find a hierarchical data organization. A novel family of mixture models is proposed which explain the observed data by a finite number of shared aspects or clusters. This provides a common framework for statistical inference and structure discovery and also includes several recently proposed models as special cases. Adopting the maximum likelihood principle, EM algorithms are derived to fit the model parameters. We develop improved versions of EM which largely avoid overfitting problems and overcome the inherent locality of EM-based optimization.Among the broad variety of possible applications, e.g., in information retrieval, natural language processing, data mining, and computer vision, we have chosen document retrieval, the statistical analysis of noun/adjective co-occurrence and the unsupervised segmentation of textured images to test and evaluate the proposed algorithms.
BibTeX:
@techreport{Hofmann1998d,
  author = {Thomas Hofmann and Jan Puzicha},
  title = {Statistical Models for Co-occurrence Data},
  year = {1998},
  number = {1625}
}
Ketterer, J., Puzicha, J., Held, M., Fischer, M., Buhmann, J. M. & Fellner, D. On Spatial Quantization of Color Images 1998 European Conference on Computer Vision   inproceedings PDF  
Abstract: Image quantization and dithering are fundamental image processing problems in computer vision and graphics. Both steps are generally performed sequentially and, in most cases, independent of each other. Color quantization with a pixel-wise defined distortion measure and the dithering process with its local neighborhood typically optimize different quality criteria or, frequently, follow a heuristic approach without reference to any quality measure. In this paper we propose a new model to simultaneously quantize and dither color images. The method is based on a rigorous cost-function approach which optimizes a quality criterion derived from a simplified model of human perception. Optimizations are performed by an efficient multiscale procedure which substantially alleviates the computational burden. The quality criterion and the optimization algorithms are evaluated on a representative set of artificial and real-world images thereby showing a significant image quality improvement over standard color reduction approaches.
BibTeX:
@inproceedings{Ketterer1998,
  author = {Jens Ketterer and Jan Puzicha and Marcus Held and Martin Fischer and Joachim M. Buhmann and Dieter Fellner},
  title = {On Spatial Quantization of Color Images},
  booktitle = {European Conference on Computer Vision},
  year = {1998},
  pages = {563-577}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. Discrete Mixture Models for Unsupervised Image Segmentation 1998 Jahrestagung der Deutsche Arbeitsgemeinschaft für Mustererkennung (DAGM'98)   inproceedings PDF  
Abstract: This paper introduces a novel statistical mixture model for probabilistic clustering of histogram data and, more generally, for the analysis of discrete co-occurrence data. Adopting the maximum likelihood framework, an alternating maximization algorithm is derived which is combined with annealing techniques to overcome the inherent locality of alternating optimization schemes. We demonstrate an application of this method to the unsupervised segmentation of textured images based on local empirical distributions of Gabor coefficients. In order to accelerate the optimization process an efficient multiscale formulation is utilized. We present benchmark results on a representative set of Brodatz mondrians and real-world images.
BibTeX:
@inproceedings{Puzicha1998,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {Discrete Mixture Models for Unsupervised Image Segmentation},
  booktitle = {Jahrestagung der Deutsche Arbeitsgemeinschaft f\"ur Mustererkennung (DAGM'98)},
  year = {1998}
}
Buhmann, J. M. & Hoffman, T. Robust Vector Quantization by Competitive Learning 1997 International Conference on Acoustics, Speech and Signal Processing ICASSP'97   inproceedings PDF  
Abstract: Competitive neural networks can be used to efficiently quantize image and video data. We discuss a novel class of vector quantizers which perform noise robust data compression. The vector quantizers are trained to simultaneously compensate channel noise and code vector elimination noise. The training algorithm to estimate code vectors is derived by the maximum entropy principle in the spirit of deterministic annealing. We demonstrate the performance of noise robust codebooks with compression results for a teleconferencing system on the basis of a wavelet image representation.
BibTeX:
@inproceedings{Buhmann1997,
  author = {Joachim M. Buhmann and Thomas Hoffman},
  title = {Robust Vector Quantization by Competitive Learning},
  booktitle = {International Conference on Acoustics, Speech and Signal Processing ICASSP'97},
  year = {1997}
}
Buhmann, J. M. Stochastic Algorithms for Exploratory Data Analysis: Data Clustering and Data Visualization 1997   inbook PDF  
Abstract: Iterative, EM-type algorithms for data clustering and data visualization are derived on the basis of the maximum entropy principle. These algorithms allow the data analyst to detect structure in vectorial or relational data. Conceptually, the clustering and visualization procedures are formulated as combinatorial or continuous optimization problems which are solved by stochastic optimization.
BibTeX:
@inbook{Buhmann1997a,
  author = {Joachim M. Buhmann},
  title = {Stochastic Algorithms for Exploratory Data Analysis: Data Clustering and Data Visualization},
  year = {1997},
  pages = {333-333}
}
Held, M. & Buhmann, J. M. Unsupervised On-Line Learning of Decision Trees for Hierarchical Data Analysis 1997 Advances in Neural Information Processing Systems (NIPS)   inproceedings PDF  
Abstract: An adaptive on-line algorithm is proposed to estimate hierarchical data structures for non-stationary data sources. The approach is based on the principle of minimum cross entropy to derive a decision tree for data clustering and t employs a metalearning idea (learning of learning) to adapt to changes in data characteristics. Its efficiency is demonstrated by grouping non-stationary artifical data and by hierarchical segmentation of LANDSAT images.
BibTeX:
@inproceedings{Held1997,
  author = {Marcus Held and Joachim M. Buhmann},
  title = {Unsupervised On-Line Learning of Decision Trees for Hierarchical Data Analysis},
  booktitle = {Advances in Neural Information Processing Systems (NIPS)},
  year = {1997},
  pages = {514-520}
}
Hofmann, T., Puzicha, J. & Buhmann, J. M. Deterministic Annealing for Unsupervised Texture Segmentation 1997 International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'97)   inproceedings PDF  
Abstract: In this paper a rigorous mathematical framework of deterministic annealing and mean-field approximation is presented for a general class of partitioning, clustering and segmentation problems. We describe the canonical way to derive efficient optimization heuristics, which have a broad range of possible applications in computer vision, pattern recognition and data analysis. In addition, we prove novel convergence results. As a major practical application we present a new approach to the problem of unsupervised texture segmentation which relies on statistical tests as a measure of homogeneity. More specifically, this results in a formulation of texture segmentation as a pairwise data clustering problem with a sparse neighborhood structure. We discuss and compare different clustering objective functions, which are systematically derived from invariance principles. The quality of the novel algorithms is empirically evaluated on a large database of Brodatz-like micro-texture mixtures and on a representative set of real-word images.
BibTeX:
@inproceedings{Hofmann1997,
  author = {Thomas Hofmann and Jan Puzicha and Joachim M. Buhmann},
  title = {Deterministic Annealing for Unsupervised Texture Segmentation},
  booktitle = {International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'97)},
  year = {1997},
  pages = {213-228}
}
Hofmann, T. & Buhmann, J. M. Pairwise Data Clustering by Deterministic Annealing 1997 IEEE Transactions on Pattern Analysis and Machine Intelligence   article PDF  
Abstract: Partitioning a data set and extracting hidden structure from the data arises in different application areas of pattern recognition and image processing. Pairwise data clustering is a combinatorial optimisation method for data grouping which extracts structure from proximity data. We descibe a deterministic annealing approach to pairwise data clustering which shares the robustness properties of maximum entropy inference. The resulting Gibbs probability distributions are estimated by meanfield approximation, a well-known technique from statistical physics. A new algorithm to group dissimilarity data and to simultanously embed these data in a Euclidian vector space is discussed which can be used for dimension reduction and data visualisation. The suggested algorithms have been implemented to analyse dissimilarity data from protein analysis and from linguistics. Furthermore, pairwise data clustering is used to segment textured images.
BibTeX:
@article{Hofmann1997a,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Pairwise Data Clustering by Deterministic Annealing},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {1997},
  volume = {19},
  number = {1},
  pages = {1-14}
}
Hofmann, T. & Buhmann, J. M. Active Data Clustering 1997 Advances in Neural Information Processing Systems (NIPS)   inproceedings PDF  
Abstract: Active Data Clustering is a novel technique for clustering proximity data which utilizes principles from sequential experiment design in order to interleave data generation and data analysis. The proposed active data sampling strategy is based on the expected value of information, a concept rooting in statistical decision theory. This is considered to be an important step towards the analysis of large-scale data sets, because it offers a way to overcome the inherent data sparseness of proximity data. We present applications to unsupervised texture segmentation in computer vision and information retrieval in document databases.
BibTeX:
@inproceedings{Hofmann1997b,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Active Data Clustering},
  booktitle = {Advances in Neural Information Processing Systems (NIPS)},
  year = {1997},
  pages = {528-534}
}
Hofmann, T., Puzicha, J. & Buhmann, J. M. An Optimization Approach to Unsupervised Hierarchical Texture Segmentation 1997 International Conference on Image Processing (ICIP '97)   inproceedings PDF  
Abstract: In this paper we introduce a novel optimization framework for hierarchical data clustering which is applied to the problem of unsupervised texture segmentation. The proposed objective function assesses the quality of an image partitioning simultaneously at different resolution levels. A novel model selection criterion to select significant image structures from various scales is proposed. As an efficient deterministic optimization heuristic a mean-field annealing algorithm is derived.
BibTeX:
@inproceedings{Hofmann1997c,
  author = {Thomas Hofmann and Jan Puzicha and Joachim M. Buhmann},
  title = {An Optimization Approach to Unsupervised Hierarchical Texture Segmentation},
  booktitle = {International Conference on Image Processing (ICIP '97)},
  year = {1997}
}
Klock, H. & Buhmann, J. M. Multidimensional Scaling by Deterministic Annealing 1997 International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'97)   inproceedings PDF  
Abstract: Multidimensional scaling addresses the problem how proximity data can be faithfully visualized as points in a low-dimensional Euclidian space. The quality of a data embedding is measured by a cost function called stress which compares proximity values with Euclidian distances of the respective points. We present a novel deterministic annealing algorithm to efficiently determine embedding coordinates for this continuous optimization problem. Experimental results demonstrate the superiority of the optimization technique compared to conventional gradient descent methods. Furthermore, we propose a transformation of dissimilarities to reduce the mismatch between a high-dimensional data space and a low-dimensional embedding space.
BibTeX:
@inproceedings{Klock1997,
  author = {Hansj\"org Klock and Joachim M. Buhmann},
  title = {Multidimensional Scaling by Deterministic Annealing},
  booktitle = {International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'97)},
  year = {1997},
  pages = {245-260}
}
Klock, H.-J., Polzer, A. & Buhmann, J. M. Region-Based Motion Compensated 3D-Wavelet Transform Coding of Video 1997 IEEE International Conference on Image Processing (ICIP '97)   inproceedings PDF  
Abstract: We present a low bit-rate video compression system that integrates region-based coding with a spatio-temporal wavelet transform. The proposed system is designed for monitoring and video-phone applications. It distinguishes between moving foreground and static background, but image segmentation might also be based on other sources. The regions are encoded in separate layers using a chroma-keying technique that allows a controlled lossy recovery of the boundaries. A 3D wavelet transform is applied to a group of frames of the predictor residual signal. Statistical dependencies of transform coefficients extracted from different image subbands are captured by conditional probability models. Without the layered coding, the system performs superior compared to the recent H.263 standard for very low bit-rate coding. The layered coding causes a small degradation in visual quality at the same bit-rate.
BibTeX:
@inproceedings{Klock1997a,
  author = {Hans-J\"org Klock and Andreas Polzer and Joachim M. Buhmann},
  title = {Region-Based Motion Compensated 3D-Wavelet Transform Coding of Video},
  booktitle = {IEEE International Conference on Image Processing (ICIP '97)},
  year = {1997}
}
Polzer, A., Klock, H.-J. & Buhmann, J. Video-Coding by Region-Based Motion Compensation and Spatio-temporal wavelet transform 1997 IEEE International Conference on Image Processing (ICIP '97)   inproceedings PDF  
Abstract: We present a low bit-rate video compression system that integrates region-based motion estimation and motion compensation with spatio-temporal wavelet transform coding. The paper focusses on the motion segmentation module, which determines maximum likelihood estimates of region motion parameters employing the Expectation Maximization (EM) algorithm and mean field techniques. Preliminary results show the competitiveness of this approach.
BibTeX:
@inproceedings{Polzer1997,
  author = {Andreas Polzer and Hans-J\"org Klock and Joachim Buhmann},
  title = {Video-Coding by Region-Based Motion Compensation and Spatio-temporal wavelet transform},
  booktitle = {IEEE International Conference on Image Processing (ICIP '97)},
  year = {1997}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. Deterministic Annealing: Fast Physical Heuristics for Real-Time Optimization of Large Systems 1997 15th IMACS World Conference on Scientific Computation, Modelling and Applied Mathematics   inproceedings PDF  
Abstract: This paper systematically investigates the heuristical optimization technique known as deterministic annealing. This method is applicable to a large class of assignment and partitioning problems. Moreover, the established theoretical results, as well as the general algorithmic solution scheme, are largely independent of the objective functions under consideration. Deterministic annealing is derived from strict minimization principles, including a rigorous convergence analysis. We stress the close relation to homotopy methods, and discuss some of the most important strengths and weaknesses in this framework. Optimization results for unsupervised texture segmentation are presented for an autonomous robotics application.
BibTeX:
@inproceedings{Puzicha1997,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {Deterministic Annealing: Fast Physical Heuristics for Real-Time Optimization of Large Systems},
  booktitle = {15th IMACS World Conference on Scientific Computation, Modelling and Applied Mathematics},
  year = {1997}
}
Puzicha, J., Hofmann, T. & Buhmann, J. M. Non-parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval 1997 IEEE International Conference on Computer Vision and Pattern Recognition   inproceedings PDF  
Abstract: In this paper we propose and examine non-parametric statistical tests to define similarity and homogeneity measures for textures. The statistical tests are applied to the coefficients of images filtered by a multi-scale Gabor filter bank. We will demonstrate that these similarity measures are useful for both, texture based image retrieval and for unsupervised texture segmentation, and hence offer an unified approach to these closely related tasks. We present results on Brodatz-like micro-textures and a collection of real-word images.
BibTeX:
@inproceedings{Puzicha1997a,
  author = {Jan Puzicha and Thomas Hofmann and Joachim M. Buhmann},
  title = {Non-parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval},
  booktitle = {IEEE International Conference on Computer Vision and Pattern Recognition},
  year = {1997},
  pages = {267-272}
}
Puzicha, J. & Buhmann, J. M. Multiscale Annealing for Real-Time Unsupervised Texture Segmentation 1997   techreport PDF  
Abstract: We derive real-time global optimization methods for several clustering optimization problems used in unsupervised texture segmentation. Speed is achieved by exploiting the topological relation of features to design a multiscale optimization technique, while accuracy and global optimization properties are gained using a deterministic annealing method. Coarse grained cost functions are derived for both central and sparse pairwise clustering, where the problem of coarsening sparse random graphs is solved by the concept of structured randomization. Annealing schedules and coarse-to-fine optimization are tightly coupled by a statistical convergence criterion derived from computational learning theory. The algorithms are benchmarked on Brodatz-like micro-texture mixtures. Results are presented for an autonomous robotics application.
BibTeX:
@techreport{Puzicha1997b,
  author = {Jan Puzicha and Joachim M. Buhmann},
  title = {Multiscale Annealing for Real-Time Unsupervised Texture Segmentation},
  year = {1997},
  number = {IAI-TR-97-4}
}
Fröhlinghaus, T. & Buhmann, J. M. Real-Time Phase-Based Stereo for a Mobile Robot 1996 First Euromicro Workshop on Advanced Mobile robots   inproceedings PDF  
Abstract: The performance of a mobile robot crucially depends on the accuracy, duration and reliability of its sensor interpretation. A major source of information are CCD-cameras which provide a detailed view of the robot's environment. This paper presents a real-time stereo algorithm implemented on the mobile robot Rhino of the University of Bonn. The algorithm exploit the phases of wavelet-filtered image pairs to localize edges and to estimate their disparities with subpixel accuracy. The disparities are computed by an initial search for corresponding points within a given interval and a subsequent measurement of phase-differences. The real-time constraints of autonomous object detection and navigation are fulfilled by partially implementing the stereo algorithm on a pipeline computer Datacube. Experimental results on real world scenes under real world conditions demonstrate the stereo algorithm's robustness and suitability for autonomous robot applications.
BibTeX:
@inproceedings{Frohlinghaus1996,
  author = {Thorsten Fr\"ohlinghaus and Joachim M. Buhmann},
  title = {Real-Time Phase-Based Stereo for a Mobile Robot},
  booktitle = {First Euromicro Workshop on Advanced Mobile robots},
  year = {1996},
  pages = {178-185}
}
Hofmann, T. & Buhmann, J. M. An Annealed Neural Gas Network for Robust Vector Quantization 1996 International Conference on Artificial Neural Networks ICANN96   inproceedings PDF  
Abstract: Vector quantization, a central topic in data compression, deals with the problem of encoding an information source or a sample of data vectors by means of a finite codebook, such that the average distortion is minimized. We introduce a common framework, based on maximum entropy inference to derive a deterministic annealing algorithm for robust vector quantization. The objective function for codebook design is extended to take channel noise and bandwidth limitations into account. Formulated as an on--line problem it is possible to derive learning rules for competitive neural networks. The resulting update rule is a generalization of the `neural gas' model. The foundation in coding theory allows us to specify an optimality criterion for the `neural gas' update rule.
BibTeX:
@inproceedings{Hofmann1996,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {An Annealed Neural Gas Network for Robust Vector Quantization},
  booktitle = {International Conference on Artificial Neural Networks ICANN96},
  year = {1996},
  pages = {151-156}
}
Hofmann, T. & Buhmann, J. M. Inferring Hierarchical Clustering Structures by Deterministic Annealing 1996 Second International Conference on Knowledge Discovery and Data Mining KDD'96   inproceedings PDF  
Abstract: The unsupervised detection of hierarchical structures is a major topic in unsupervised learning and one of the key questions in data analysis and representation. We propose a novel algorithm for the problem of learning decision trees for data clustering and related problems. In contrast to many other methods based on successive tree growing and pruning, we propose a completely non--greedy technique based on an explicit objective function. Applying the principles of maximum entropy and minimum cross entropy, a deterministic annealing algorithm is derived in a meanfield approximation. This technique allows us to canonically superimpose tree structures and to fit parameters to averaged or `fuzzified' trees.
BibTeX:
@inproceedings{Hofmann1996a,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Inferring Hierarchical Clustering Structures by Deterministic Annealing},
  booktitle = {Second International Conference on Knowledge Discovery and Data Mining KDD'96},
  year = {1996},
  pages = {363-366}
}
Hofmann, T., Puzicha, J. & Buhmann, J. M. Unsupervised Segmentation of Textured Images by Pairwise Data Clustering 1996 International Conference on Image Processing ( ICIP '96 )   inproceedings PDF  
Abstract: We propose a novel approach to unsupervised texture segmentation, which is formulated as a combinatorial optimization problem known as pairwise data clustering with a sparse neighborhood structure. Pairwise dissimilarities between texture blocks are measured in terms of distribution differences of multi--resolution features. The feature vectors are based an a Gabor wavelet image representation.To efficiently solve the data clustering problem a deterministic annealing algorithm based on a meanfield approximation is derived. An application to Brodatz--like microtexture mixtures is shown. We statistically adress the questions of adequacy of the proposed cost function and the quality of the deterministic annealing algorithm compared with its stochastic variants.
BibTeX:
@inproceedings{Hofmann1996b,
  author = {Thomas Hofmann and Jan Puzicha and Joachim M. Buhmann},
  title = {Unsupervised Segmentation of Textured Images by Pairwise Data Clustering},
  booktitle = {International Conference on Image Processing ( ICIP '96 )},
  year = {1996},
  volume = {III},
  pages = {137-140}
}
Klock, H. & Buhmann, J. M. Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach 1996   techreport  
Abstract: Multidimensional scaling addresses the problem how proximity data can be faithfully visualized as points in a low-dimensional Euclidian space. The quality of a data embedding is measured by a stress function which compares proximity values with Euclidian distances of the respective points. The corresponding minimization problem is non-convex and sensitive to local minima. We present a novel deterministic annealing algorithm for the frequently used objective SSTRESS and for Sammon mapping , derived in the framework of maximum entropy estimation. Experimental results demonstrate the superiority of our optimization technique compared to conventional gradient descent methods.
BibTeX:
@techreport{Klock1996,
  author = {Hansj\"org Klock and Joachim M. Buhmann},
  title = {Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach},
  year = {1996},
  number = {IAI-TR-96-8}
}
Puzicha, J., Goerke, N. & Eckmiller, R. Optimal Trajectory Generation for an Industrial Robot by Markovian Networks 1996 International Conference on Neural Information Processing (ICONIP'96)   inproceedings PDF  
Abstract: Optimal trajectory generation can be represented as a constrained variational problem posed simultaneously in cartesian and joint coordinate spaces. Markovian Networks are presented as a class of neural networks especially suited for solving general constrained variational problems. By incorporation of the kinematic map an iterative network dynamic is created, which gradually converges to an optimal solution. The capability of this approach is demonstrated by generating optimal 6--DOF movements along surfaces for an industrial robot arm with remarkable improvements compared to a standard algorithm.
BibTeX:
@inproceedings{Puzicha1996,
  author = {Jan Puzicha and Nils Goerke and Rolf Eckmiller},
  title = {Optimal Trajectory Generation for an Industrial Robot by Markovian Networks},
  booktitle = {International Conference on Neural Information Processing (ICONIP'96)},
  year = {1996},
  pages = {995-998}
}
Puzicha, J., Hofmann, T. & Buhmann, J. Unsupervised Texture Segmentation on the Basis of Scale Space Features 1996   techreport PDF  
Abstract: A novel approach to unsupervised texture segmentation is presented, which is formulated as a combinatorial optimization problem known as sparse pairwise data clustering. Pairwise dissimilarities between texture blocks are measured by scale space features, i.e., multi-resolution edges. These scale space features are computed by a Gabor filter bank tuned to spatial frequencies. To solve the data clustering problem a deterministic annealing technique is applied. This approach is examined from the viewpoint of scale space theory. Based on a meanfield approximation an efficient algorithm is derived. We present an application of the proposed algorithm to Brodatz--like microtexture collages.
BibTeX:
@techreport{Puzicha1996a,
  author = {Jan Puzicha and Thomas Hofmann and Joachim Buhmann},
  title = {Unsupervised Texture Segmentation on the Basis of Scale Space Features},
  year = {1996},
  number = {DIKU 96/19}
}
Buhmann, J. M. Oscillatory Associative Memories 1995 Handbook of Brain Theory & Neural Networks   inbook PDF  
Abstract: Assemblies of cooperating binary units have been postulated as the basic building blocks of associative memories. Artificial neural networks with a simple dynamics evolve from initial states to predefined fixed points, the memory traces. Storage and retrieval in these neural networks with fixed point attractors are limited to one attern at a time. Biological and functional considerations especially in olfactory cortex motivate oscillatory neural network dynamics which model experimentally observed neural activity patterns in associative recall tasks. Binding features to stored patterns when several memory traces are coactivated requires a network dynamics with oscillatory or even chaotic activity patterns.
BibTeX:
@inbook{Buhmann1995,
  author = {Joachim M. Buhmann},
  title = {Oscillatory Associative Memories},
  booktitle = {Handbook of Brain Theory \& Neural Networks},
  year = {1995},
  pages = {333-333}
}
Buhmann, J. M., Burgard, W., Cremers, A. B., Fox, D., Hofmann, T., Schneider, F., Strikos, J. & Thrun, S. The Mobile Robot Rhino 1995 AI Magazin   article PDF  
Abstract: Rhino was the University of Bonn's entry in the 1994 AAAI mobile robot competition. Rhino is a mobile robot designed for indoor navigation and manipulation tasks. The general scientific goal of the Rhino project is the development and the analysis of autonomous and complex learning systems. This paper briefly describes the major components of the Rhino control software, as they were exhibited at the competition. It also sketches the basic philosophy of the Rhino architecture, and discusses some of the lessons that we learned during the competition.
BibTeX:
@article{Buhmann1995a,
  author = {Joachim M. Buhmann and Wolfram Burgard and Armin B. Cremers and Dieter Fox and Thomas Hofmann and Frank Schneider and Jiannis Strikos and Sebastian Thrun},
  title = {The Mobile Robot Rhino},
  journal = {AI Magazin},
  year = {1995},
  volume = {16},
  number = {1},
  pages = {1}
}
Hofmann, T. & Buhmann, J. M. Hierarchical Pairwise Data Clustering by Mean-Field Annealing 1995 International Conference on Artificial Neural Networks (ICANN'95)   inproceedings PDF  
Abstract: Partitioning a data set and extracting hidden structure arises in different application areas of pattern recognition, data analysis and image processing. We formulate data clustering for data characterized by pairwise dissimilarity values as an assignement problem with an objective function to be minimized. An extension to tree-structured clustering is proposed which allows a hierarchical grouping of data. Deterministic annealing algorithms are derived for unconstrained and tree-structured pairwise clustering.
BibTeX:
@inproceedings{Hofmann1995,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Hierarchical Pairwise Data Clustering by Mean-Field Annealing},
  booktitle = {International Conference on Artificial Neural Networks (ICANN'95)},
  year = {1995},
  pages = {197-202}
}
Hofmann, T. & Buhmann, J. M. Multidimensional Scaling and Data Clustering 1995 Advances in Neural Information Processing Systems 7 (NIPS'94)   inproceedings PDF  
Abstract: Visualizing and structuring pairwise dissimilarity data are difficult combinatorial problems known as multidimensional scaling or pairwise data clustering. Algorithms for embedding dissimilarity data sets in Euclidian space, for clustering these data and for actively selecting data to support the clustering process are discussed in the maximum entropy framework. Active data selection provides a strategy to discover structure in a data set efficiently with partially unknown data.
BibTeX:
@inproceedings{Hofmann1995a,
  author = {Thomas Hofmann and Joachim M. Buhmann},
  title = {Multidimensional Scaling and Data Clustering},
  booktitle = { Advances in Neural Information Processing Systems 7 (NIPS'94)},
  year = {1995},
  pages = {104-111}
}
Buhmann, J. M. & Hofmann, T. A Maximum Entropy Approach to Pairwise Data Clustering 1994 International Conference on Pattern Recognition   inproceedings PDF  
Abstract: Partitioning a set of data points which are characterized by their mutual dissimilarities instead of an explicit coordinate representation is a difficult, NP-hard combinatorial optimization problem. We formulate this optimization problem of a pairwise clustering cost function in the maximum entropy framework using a variational principle to derive corresponding data partitionings in a d-dimensional Euclidian space. This approximation solves the embedding problem and the grouping of these data into clusters simultaneously and in a selfconsistent fashion.
BibTeX:
@inproceedings{Buhmann1994,
  author = {Joachim M. Buhmann and Thomas Hofmann},
  title = {A Maximum Entropy Approach to Pairwise Data Clustering},
  booktitle = {International Conference on Pattern Recognition},
  year = {1994},
  pages = {207-212}
}
Buhmann, J. M., Lades, M. & Eeckmann, F. Illumination-Invariant Face Recognition with a Contrast Sensitive Silicon Retina 1994 Advances in Neural Information Processing Systems (NIPS)   inproceedings PDF  
Abstract: Changes in lighting conditions strongly effect the performance and reliability of computer vision systems. We report face recognition results under drastically changing lightning conditions for a computer vision system which concurrently uses a contrast sensitive silicon retina and a conventional, gain controlled CCD camera. For both input devices the face recognition system employs an elastic matching algorithm with wavelet based features to classify unknown faces. To assess the effect of analog on-chip preprocessing by the silicon retina the CCD images have been igitally preprocessedwith a bandpass filter to adjust the power spectrum. The silicon retina with its ability to adjust sensitivity increases the recognition rate up to 50 percent. These comparative experiments demonstrate that preprocessing with an analog VLSI silicon retina generates image data enriched with object-constant features.
BibTeX:
@inproceedings{Buhmann1994a,
  author = {Joachim M. Buhmann and Martin Lades and Frank Eeckmann},
  title = {Illumination-Invariant Face Recognition with a Contrast Sensitive Silicon Retina},
  booktitle = {Advances in Neural Information Processing Systems (NIPS)},
  year = {1994},
  volume = {6},
  pages = {769-776}
}
Buhmann, J. M. & Kühnel, H. Complexity Optimized Data Clustering by Competitive Neural Networks 1993 Neural Computation   article  
BibTeX:
@article{Buhmann1993,
  author = {Joachim M. Buhmann and Hans K{\"u}hnel},
  title = {Complexity Optimized Data Clustering by Competitive Neural Networks},
  journal = {Neural Computation},
  year = {1993},
  volume = {5},
  pages = {75-88}
}
Buhmann, J. M. & Kühnel, H. Vector Quantization with Complexity Costs 1993 IEEE Transactions on Information Theory   article PDF  
Abstract: Vector quantization is a data compression method where a set of data points is encoded by a reduced set of reference vectors, the codebook. We discuss a vector quantization strategy which jointly optimizes distortion errors and the codebook complexity, thereby, determining the size of the codebook. A maximum entropy estimation of the cost function yields an optimal number of reference vectors, their positions and their assignement probabilities. The dependence of the codebook density on the data density for different complexity measures is investigated in the limit of asymptotic quantization levels. How different complexity measures influence the efficiency of vector quantization is studied for the task of image compression, i.e., we quantize the wavelet coefficients of gray level images and measure the reconstruction error. Our approach establishes a unifying framework for different quantization methods like K-means clustering and its fuzzy version, entropy constrained vector quantization or topological feature maps and competitive neural networks.
BibTeX:
@article{Buhmann1993a,
  author = {Joachim M. Buhmann and Hans K\"uhnel},
  title = {Vector Quantization with Complexity Costs},
  journal = {IEEE Transactions on Information Theory},
  year = {1993},
  volume = {39},
  pages = {1133-1145}
}
Lades, M., Vorbrüggen, J. C., Buhmann, J. M., Lange, J., von der Malsburg, C., Würtz, R. P. & Konen, W. Distortion Invariant Object Recognition in the Dynamic Link Architecture 1993 IEEE Transactions on Computers   article  
BibTeX:
@article{Lades1993,
  author = {Martin Lades and Jan C. Vorbr\"uggen and Joachim M. Buhmann and J\"org Lange and Christoph {von der Malsburg} and Rolf P. W\"urtz and Wolfgang Konen},
  title = {Distortion Invariant Object Recognition in the Dynamic Link Architecture},
  journal = {IEEE Transactions on Computers},
  year = {1993},
  volume = {42},
  pages = {300-311}
}
Arbib, M. A. & Buhmann, J. M. Neural Networks 1992 Encyclopedia of Artificial Intelligence   inproceedings  
BibTeX:
@inproceedings{Arbib1992,
  author = {Michael A. Arbib and Joachim M. Buhmann},
  title = {Neural Networks},
  booktitle = {Encyclopedia of Artificial Intelligence},
  publisher = {John Wiley},
  year = {1992},
  volume = {2},
  pages = {1016-1060}
}
Buhmann, J. M. Neuronale Netzwerke als assoziative Speicher und als Systeme zur Mustererkennung 1988 School: Physik-Department, Technische Universität München   phdthesis  
BibTeX:
@phdthesis{Buhmann1988,
  author = {Joachim M. Buhmann},
  title = {Neuronale Netzwerke als assoziative Speicher und als Systeme zur Mustererkennung},
  school = {Physik-Department, Technische Universit\"at M\"unchen},
  year = {1988}
}

Created by JabRef on 16/04/2015.