Sophia Sanborn

Bispectral Neural Networks

2022 · arXiv (Cornell University)

We present a neural network architecture, Bispectral Neural Networks (BNNs) for learning representations that are invariant to the actions of compact commutative groups on the space over which a signal is defined. The model incorporates …

A General Framework for Robust G-Invariance in G-Equivariant Networks

2023 · arXiv (Cornell University)

We introduce a general method for achieving robust group-invariance in group-equivariant convolutional neural networks ($G$-CNNs), which we call the $G$-triple-correlation ($G$-TC) layer. The approach leverages the theory of the triple-correlation on groups, which is the …