Geometric Invariants on Position-Orientation Space with Application in Equivariant Machine Learning
Prediction of scalar properties of molecules should be invariant under Euclidean transforms.
Abstract
We present an overview of the use of geometric invariants in designing Euclidean-invariant neural networks for predicting scalar properties of molecules.
Date
Apr 16, 2025 16:20
Event
CASA Day April 2025
Location
Conferentiecentrum Eindhoven