Share Email Print

Proceedings Paper

Oscillatory neural networks for nonlinear system identification
Author(s): Ann Evenson; Travis J. McIlvenna; Mohamed L. Hambaba
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

We present connectionist classifiers that form distributed low-level knowledge representations for pattern recognition, given random feature vectors generated from dual statistically distinct sources. The classifier is a functional representation of an oscillatory network consisting of two-member clusters of model neurons whose efferent synapses may be either inhibitory or excitatory. We demonstrate the oscillatory network's performance in the context of source- dependent single speaker identification. In these tests, the backpropagation network representation learning curve began to flatten around an unacceptable error response. The oscillatory model, however, was able to discriminate accurately.

Paper Details

Date Published: 15 October 1993
PDF: 10 pages
Proc. SPIE 1960, Automatic Object Recognition III, (15 October 1993); doi: 10.1117/12.160600
Show Author Affiliations
Ann Evenson, Stevens Institute of Technology (United States)
Travis J. McIlvenna, Stevens Institute of Technology (United States)
Mohamed L. Hambaba, Stevens Institute of Technology (United States)

Published in SPIE Proceedings Vol. 1960:
Automatic Object Recognition III
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top