Browsing Computer Science (Scholarly Publications) by Subject "Vanishing gradients"
Now showing items 1-1 of 1
-
Mutual Information Decay Curves and Hyper-parameter Grid Search Design for Recurrent Neural Architectures
(2020)We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies ...