Singular Value Decomposition and Neural Networks

Bernhard Bermeitinger
Bernhard Bermeitinger
Tomas Hrycej
Tomas Hrycej

ICANN (2), pp. 153-164, 2019.

Cited by: 2|Bibtex|Views2|Links
EI

Abstract:

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.

Code:

Data:

Your rating :
0

 

Tags
Comments