Singular Value Decomposition and Neural Networks

06/27/2019

∙

by   Bernhard Bermeitinger, et al.

∙

0

∙

share

Singular Value Decomposition (SVD) constitutes a bridge between the linear algebra concepts and multi-layer neural networks---it is their linear analogy. Besides of this insight, it can be used as a good initial guess for the network parameters, leading to substantially better optimization results.