Published on Mon Feb 27 2017

Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos

We propose to study equivariance in deep neural networks through parameter symmetries. In particular, given a group that acts discretely on the input and output of a standard neural network layer, we show that

0

0

0

We propose to study equivariance in deep neural networks through parameter
symmetries. In particular, given a group