← Search

Kyle Helfrich

1 accepted papers

2018

Orthogonal Recurrent Neural Networks with Scaled Cayley Transform

ICML 2018oral

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs…