Share Email Print

Proceedings Paper

Realizing the potential of neural network implementation technologies: methods of using large neural networks
Author(s): Colin Smith
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

In the longer term amorphous silicon and other technologies are promising to allow the implementation of large neural networks directly in hardware. However, although a number of application areas, such as telecommunication network management and image recognition, could benefit from such large artificial neural networks because they require large numbers of inputs and/or outputs, it is currently difficult to determine the benefits of large networks in such application areas for the following main reasons. Firstly, design application engineers do not yet have such tool available to them; secondly, and more importantly, many popular neural network training algorithms do not scale well. This paper suggests new methods of combining many small networks to produce a large composite system capable of extending the range of problems to which neural network techniques can be applied. It shows how large networks can be used to extend the ideas of fuzzy logic so that non-linear dependences between vectors can be dealt with.

Paper Details

Date Published: 1 July 1992
PDF: 6 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140123
Show Author Affiliations
Colin Smith, British Telecom Labs. (United Kingdom)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top