NobleBlocks
Public

Layer Normalization

Published in arXiv (Cornell University) • Jul 21, 2016
Authors:
Jimmy Ba
,
Jamie Kiros
,
Geoffrey E. Hinton

Abstract

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of train...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!