In this seminar, recent papers of the machine learning literature are presented and discussed. Students will learn how to structure a scientific presentation in English which covers the key ideas of a scientific paper. An important goal of the seminar presentation is to summarize the essential ideas of the paper in sufficient depth while omitting details which are not essential for the understanding of the work. The presentation style will play an important role and should reach the level of professional scientific presentations.

Class Info


Slides (Thursday slot)

Date Student Topic
Oct 19 Ernst Oldenhof Weight Uncertainty in Neural Networks
Erik Daxberger Dropout as a Bayesian Approximation
Oct 26 Robin Spiess Uncertainties for Bayesian Deep Learning for Computer Vision
Rémi Pautrat Auto-Encoding Variational Bayes
Nov 02 Amirezza Bahreini Train Faster, Generalize Better
Jean Garret Matrix Completion has no Spurious Local Minimum
Nov 09 Antonio Orvieto Gradient Descent Learns Linear Dynamical Systems
Mohammad Reza Karimi Failures of Gradient-Based Deep Learning
Nov 16 Adyasha Dash Inherent Trade-Offs in the Fair Determination of Risk Score
Andreas Psimopoulos Deep Learning for Predicting Human Strategic Behaviour
Nov 23 Moritz Zilian Equality of Opportunity in Supervised Learning
Nov 30 Marko Trauber Why Should I Trust You? Explaining the Predictions of any Classifier
Dec 14 Timo Bräm Action-Conditional Video Prediction using Deep Networks
Yu-chen Tsai Value Iteration Networks

Use your nethz credentials to access the slides.


Professors: Prof. Joachim Buhmann, Prof. Thomas Hofmann, Prof. Andreas Krause, Prof. Gunnar Rätsch
Assistants: Dr. Rebekka Burkholz, Dr. Luis Haug, Dr. Jens Witkowski