Probabilistic Graphical Models for Image Analysis

Dr. Stefan Bauer - Autumn Semester, 2018




Course Description

This course will focus on state space models. We use a framework called probabilistic graphical models which include Bayesian Networks and Markov Random Fields. We apply the approach to time series data with a focus on latent state space models for videos. The course covers amongst others the following topics:

Time and Place

PLEASE NOTE THE NEW TIMES AND LOCATION:

Lectures Friday, 13:00-15:00 HG E 21
Exercises Tuesday, 15:00-16:00 CAG G 56

Exam

20 Minute oral exam in English.

Syllabus

Day Lecture Topics Lecture Slides Recommended Reading Background Material
Sep 21 Introduction Graphical Models Lecture 1 Bishop, Chapter 8
Sep 28 Variational Inference Lecture 2 Bishop, Chapter 9 Variational Inference: A Review for Statisticians
Oct 5 Expectation Propagation Lecture 3 Bishop, Chapter 10
Oct 12 Repetition and Stochastic Variational Inference Lecture 4 Black Box Variational Interference - AISTATS 2014
Oct 19 Sequential Data Lecture 5 Bishop, Chapter 13 A Unifying Review of Linear Gaussian Models
Oct 26 Dimensionality Reduction Lecture 6 Bishop, Chapter 12
Nov 2 Summary Dimensionality Reduction and State Space Models Lecture 7
Nov 9 Guest Lecture: Generative Adversarial Networks no slides NIPS 2016 Tutorial
Nov 16 Autoencoding Variational Bayes Lecture 9 Deep Learning, Chapter 14 Tutorial on Variational Autoencoder
Nov 23 Score Function Estimators Lecture 10
Nov 30 Evaluating Deep Representation Learning Lecture 11 Deep Learning, Chapter 15
Dec 14 Guest Lecture: Temporal Point Processses and Bayesian Non-parametrics Lecture 12a Lecture 12b
Dec 21

Resources

Primary References

C. Bishop. Pattern Recognition and Machine Learning. Springer, 2007.
Available for free from here.

I. Goodfellow, Y. Bengio and A. Courville. Deep Learning. MIT Press, 2016.
Available for free from here.

Additional references

D. Barber. Bayesian Reasoning and Machine Learning. Cambridge University Press 2012.
Covers many topics in graphical models and machine learning. Available for free from here.

M. Wainwright and M.I. Jordan. Graphical models, exponential families and variational inference. Foundations and Trends in Machine Learning 2008.
Advanced treatment of graphical models and variational inference. Available free from here.

Frequently Asked Questions

Please ask your questions through the Piazza Forum

Contact

Dr. Stefan Bauer