MLI Group
Machine Learning and Artificial Intelligence

Teaching

In this winter semester 2023/24 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

To subscribe to the lecture please visit the ILIAS course website. The course material will be published on ILIAS throughout the semester as well.

Tentative Schedule
25.10.231. Introduction and Overview
01.11.23No lecture (All Saints’ Day)
08.11.232. Fundamentals of Deep Learning I
15.11.233. Fundamentals of Deep Learning II
22.11.234. High-Dimensional Learning
29.11.235. Geometric Priors I
06.12.236. Geometric Priors II
13.12.237. Graphs & Sets I
20.12.238. Graphs & Sets II
27.12.23No lecture (Merry Christmas!)
03.01.24No lecture (Happy New Year!)
10.01.249. Grids
17.01.2410. Groups
24.01.2411. Geodesics and Manifolds
31.01.2412. Gauges
07.02.2413. Beyond Groups
14.02.2414. Conclusions, Recap and Questions

Switch to the German homepage or stay on this page