Share Email Print

Proceedings Paper

Accelerating learning in a neural network for sonar signal classification
Author(s): Sridhar Narayan; Gene A. Tagliarini; Edward W. Page
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

Ensemble encoding employs multiple, overlapping receptive fields to yield a distributed representation of analog signals. The effect of ensemble encoding on learning in multi-layer perceptron (MLP) networks is examined by applying it to a neural learning benchmark, sonar signal classification. Results suggest that, when used to encoded input patterns, ensemble encoding can accelerate learning and improve classification accuracy in MLP networks.

Paper Details

Date Published: 19 August 1993
PDF: 5 pages
Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152623
Show Author Affiliations
Sridhar Narayan, Clemson Univ. (United States)
Gene A. Tagliarini, Clemson Univ. (United States)
Edward W. Page, Clemson Univ. (United States)

Published in SPIE Proceedings Vol. 1966:
Science of Artificial Neural Networks II
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top