Paper
3 May 1988 Improving The Performance Of Neural Networks
Henri H Arsenault, Yunlong Sheng, Alexandre Jouan, Claude Lejeune
Author Affiliations +
Proceedings Volume 0882, Neural Network Models for Optical Computing; (1988) https://doi.org/10.1117/12.944103
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
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.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Henri H Arsenault, Yunlong Sheng, Alexandre Jouan, and Claude Lejeune "Improving The Performance Of Neural Networks", Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); https://doi.org/10.1117/12.944103
Lens.org Logo
CITATIONS
Cited by 3 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neurons

Neural networks

Content addressable memory

Binary data

Pattern recognition

Optical computing

Fourier transforms

Back to Top