uvagedl.github.io

UvA - An Introduction to Group Equivariant Deep Learning

Welcome to the public page for the mini-course on Group Equivariant Deep Learning. The course is currently still a work in progress, so please forgive me for the occasional sloppyness in the provided materials. In the upcoming months I will regularly update them. The most important piece of material in this course are the lecture notes.

Erik Bekkers

Tutorials and other deep learning topics:

• See Deep Learning 2 Course Website for our GEDL tutorials, but also for materials on other interesting topics such as Bayesian Deep Learning, Deep Probabilstic Models, Causality, Dynamical Systems, etc. Please check them out as well!

Youtube playlist:

• Youtube playlist

Lecture slide deck:

• Lecture 1: Regular group convolutional neural networks
  • Lecture 1.1
  • Lecture 1.2
  • Lecture 1.3
  • Lecture 1.4
  • Lecture 1.5
  • Lecture 1.6
  • Lecture 1.7
• Lecture 2: Steeragble group convolutional neural networks
  • Lecture 2.1
  • Lecture 2.2
  • Lecture 2.3
  • Lecture 2.4
  • Lecture 2.5
  • Lecture 2.6
  • Lecture 2.7
• Lecture 3: Equivariant graph neural networks
  • Lecture 3.1
  • Lecture 3.2
  • Lecture 3.3
  • Lecture 3.4
  • Lecture 3.5
  • Lecture 3.6
  • Lecture 3.7

Lecture notes (work in progress…):

• Lecture notes

Slides and lecture recording (summer school):

• Slides and corresponding link to recorded talk
• Slides talk at Lorentz Center

Colab assignments (to be updated…):

• [Library demos] Please check out these amazing libraries: e2cnn and e3nn
• Colab Assigment 1 (SE(2) gconvs): Thanks to Gabriele Cesa for providing these! These assignments were used in the Geometric-Deep Learning Course
• Colab Assigment 2 (SE(3) steerable gconvs