Share Email Print

Proceedings Paper

Improving The Performance Of Neural Networks
Author(s): Henri H Arsenault; Yunlong Sheng; Alexandre Jouan; Claude Lejeune
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

The performance of neural networks used for pattern recognition and classification may be improved by introducing some capacity for invariance into the network. Two measures of similarity and their relationship to the network architecture are discussed. A very efficient neural network that may be used not only as a content-addressable memory but as a general symbolic substitution network is discussed. In addition to invariance to input errors, invariance to translations and rotations are considered. This may be accomplished by modifying the network itself, or changing the interconnection scheme, or by means of some pre-processing of the input data. In some cases the preprocessing could be done by the network itself or by another network, or by optical means. The techniques discussed include the introduction of more input neurons, the preprocessing of data by means of invariant matched filters, the use of new invariant image representations and the projection of input data on stored invariant principal components. The trade-offs involved in the various proposed schemes are discussed.

Paper Details

Date Published: 3 May 1988
PDF: 8 pages
Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); doi: 10.1117/12.944103
Show Author Affiliations
Henri H Arsenault, Universite Laval (Canada)
Yunlong Sheng, Universite Laval (Canada)
Alexandre Jouan, Universite Laval (Canada)
Claude Lejeune, Universite Laval (Canada)

Published in SPIE Proceedings Vol. 0882:
Neural Network Models for Optical Computing
Ravindra A. Athale; Joel Davis, Editor(s)

© SPIE. Terms of Use
Back to Top