Geometric Deep Learning
Neural architectures that encode symmetry, geometry, equivariance, and three-dimensional structure.
- How invariant attention scores, equivariant values, and energy-based force prediction turn geometric Transformers into practical interatomic potentials.
- How canonicalization, local frames, frame averaging, and probabilistic symmetrization create geometric models—and why continuity is difficult.
- Flow matching beyond Euclidean space, from tangent velocity fields and geodesic conditional paths to product manifolds for molecular geometry.
- How geometric graph networks move from invariant distances and angles to equivariant coordinates and vector channels—and what directionality buys.
- How irreducible rotation types, spherical harmonics, and Clebsch–Gordan tensor products create expressive equivariant neural-network layers.
- Understanding the spherical equivariant layers that power modern molecular neural networks, from group theory foundations to Clebsch-Gordan tensor products.