Equivariant neural networks (Cohen-Welling)

Layer 1 — Physicsin the machine-learning-physics subtree

Cohen-Welling 2016 / Bronstein 2021 'Geometric Deep Learning'. Symmetry-preserving NN architectures (rotation / translation / SE(3)). Used in protein-folding (AlphaFold) + molecular-property prediction.

Related concepts

Explore Equivariant neural networks (Cohen-Welling) on the interactive knowledge graph →