Teaching
In this winter semester 2022/23 I will teach a course in Geometric Deep Learning:
2400179 – Geometric Deep Learning
This module provides students with both theoretical and practical insights into modern Deep Learning.
In particular, we focus on a novel approach for understanding deep neural networks with mathematical tools from geometry and group theory.
This enables a methodical approach to Deep Learning: starting from first principles of symmetry and invariance, we derive different network architectures for analyzing unstructured sets, grids, graphs, and manifolds.
Topics of the course include: group theory, graph neural networks, convolutional neural networks, applications of geometric deep learning in diverse fields such as geometry processing, molecular dynamics, social networks, game playing (computer Go), processing of text and speech, as well as applications in medicine.
Literature: M. M. Bronstein, J. Bruna, T. Cohen, P. Veličković. Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
https://arxiv.org/pdf/2104.13478.pdf
Parts of the course will be based on the material on https://geometricdeeplearning.com
The course material will be published on the ILIAS course website.
Click here to join the ILIAS course
Tentative Schedule | |
26.10.22 | 1. Introduction and Overview |
02.11.22 | 2. Fundamentals of Deep Learning I |
09.11.22 | 3. Fundamentals of Deep Learning II |
16.11.22 | 4. High-Dimensional Learning |
23.11.22 | 5. Geometric Priors I |
30.11.22 | 6. Geometric Priors II |
07.12.22 | 7. Graphs & Sets I |
14.12.22 | 8. Graphs & Sets II |
21.12.22 | 9. Grids |
28.12.22 | No lecture (Merry Christmas!) |
04.01.23 | No lecture (Happy New Year!) |
11.01.23 | 10. Groups |
18.01.23 | 11. Geodesics and Manifolds |
25.01.23 | 12. Gauges |
01.02.23 | 13. Beyond Groups |
08.02.23 | 14. Conclusions |
15.02.23 | 15. Recap and Questions |