Andrew Gordon Wilson

Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems

2016 · arXiv (Cornell University)

This is the Proceedings of NIPS 2016 Workshop on Interpretable Machine Learning for Complex Systems, held in Barcelona, Spain on December 9, 2016

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

2021 · arXiv (Cornell University)

Symmetries and equivariance are fundamental to the generalization of neural networks on domains such as images, graphs, and point clouds. Existing work has primarily focused on a small number of groups, such as the translation, …