Someone wanted to learn this too, so Grasp built them a personal learning path.
You can keep exploring this one or create your own
Geometric Machine Learning
Recommended resources
The freely available resources this course will direct you to.
- Pairwise Distances for Kernel Methodsmaximerobeyns.com
- torch.cdist — PyTorch main documentationdocs.pytorch.org
- What is Jacobian? | The right way of thinking derivatives and integralswww.youtube.com
- The Jacobian matrixwww.youtube.com
- 18.02 Multivariable Calculus, Fall 2007 Transcriptocw.mit.edu
- Geometric Meaning of Jacobian Matrixangeloyeo.github.io
Module 2
Symmetry, Group Actions, Invariance, and Equivariance
Module 3
Message Passing and Graph Neural Networks
Module 4
Manifolds, Laplacians, and Non-Euclidean Representations
Module 5
Representing and Preparing 3D Geometry
Module 6
Learning on Point Clouds
Module 7
Learning on Meshes and Surfaces
Module 8
E(3)- and SE(3)-Equivariant Neural Networks
Module 9
Geometric Learning in Molecules, Physics, Robotics, and Networks
Module 10
Geometric Generative Models and 3D Foundation Models
Module 11
Reading, Reproducing, and Evaluating Current Research
Module 12