PDE-based Group Equivariant Convolutional Neural Networks

1 code implementation • 24 Jan 2020 • Bart Smets, Jim Portegies, Erik Bekkers, Remco Duits

We solve the PDE of interest by a combination of linear group convolutions and non-linear morphological group convolutions with analytic kernel approximations that we underpin with formal theorems.

Data Augmentation Translation