Training multilayer perceptrons by principal component analysis

We present a training algorithm for multilayer perceptrons which relates to the technique of principal component analysis. The latter is performed with respect to a correlation matrix which is computed from the example inputs and their target outputs. For large networks the novel procedure requires far fewer examples for good generalization than traditional on-line algorithms.

MoreLess

Year of publication:	2001
Authors:	Biehl, M. ; Bunzmann, C. ; Urbanczik, R.
Published in:	Physica A: Statistical Mechanics and its Applications. - Elsevier, ISSN 0378-4371. - Vol. 302.2001, 1, p. 56-63
Publisher:	Elsevier
Subject:	Neural networks \| Machine learning \| Disordered systems

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010589587