e3nn: Euclidean Neural Networks | Mario Geiger

Join the Learning on Graphs and Geometry Reading Group: https://hannes-stark.com/logag-readin...

Paper “e3nn: Euclidean Neural Networks": https://arxiv.org/abs/2207.09453

Abstract: We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometric tensors that describe systems in 3D and transform predictably under a change of coordinate system. The core of e3nn are equivariant operations such as the TensorProduct class or the spherical harmonics functions that can be composed to create more complex modules such as convolutions and attention mechanisms. These core operations of e3nn can be used to efficiently articulate Tensor Field Networks, 3D Steerable CNNs, Clebsch-Gordan Networks, SE(3) Transformers and other E(3) equivariant networks.

Authors: Mario Geiger, Tess Smidt

Twitter Hannes:   / hannesstaerk  
Twitter Dominique:   / dom_beaini  
Twitter Valence Discovery:   / valence_ai  

Reading Group Slack: https://join.slack.com/t/logag/shared...

~

Chapters

00:00 - Intro
03:03 - What is e3nn?
03:57 - Group representations
37:15 - Spherical harmonics
48:36 - Tensor product