Decoupled Neural Interfaces using Synthetic Gradients

international conference on machine learning, 2017.

Cited by: 192|Bibtex|Views264
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Training directed neural networks typically requires forward-propagating data through a computation graph, followed by backpropagating error signal, to produce weight updates. All layers, or more generally, modules, of the network are therefore locked, in the sense that they must wait for the remainder of the network to execute forwards a...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments