Share Email Print

Proceedings Paper

Study on evaluation ways of feed-forward neural networks generalization ability
Author(s): Yanfang Li; Wei He; Huamin Yang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Generalization ability of feed-forward neural networks is discussed in this paper. Firstly, presents and certifies two practical methods for improving networks generalization ability based on theory and experiment research. Secondly, gives a measuring model of networks generalization ability with generalization error. The essential is to define a probability input model and regard the expectation error of network upon testing samples as index for measuring networks generalization ability. Computation quantity and complexity are much less compared with traditional method.

Paper Details

Date Published: 11 January 2005
PDF: 3 pages
Proc. SPIE 5642, Information Optics and Photonics Technology, (11 January 2005); doi: 10.1117/12.574709
Show Author Affiliations
Yanfang Li, Changchun Univ. of Science and Technology (China)
Wei He, Changchun Univ. of Science and Technology (China)
Huamin Yang, Changchun Univ. of Science and Technology (China)

Published in SPIE Proceedings Vol. 5642:
Information Optics and Photonics Technology
Guoguang Mu; Francis T. S. Yu; Suganda Jutamulia, Editor(s)

© SPIE. Terms of Use
Back to Top