search

gradientinstitute / aboleth

A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation
Apache License 2.0
127 stars 10 forks source link

Initialize MAP weights with glorat_uniform #185

Closed lmccalman closed 6 years ago

lmccalman commented 6 years ago

We need to scale weight layers depending on the size of the layer inputs and outputs. Initialization matters a lot!