Share Email Print

Proceedings Paper

Constrained neural network architectures for target recognition
Author(s): Donald R. Hush; Mary M. Moya; Shang-Ying Clark
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes several different types of constraints that can be placed on multilayered feedforward neural networks which are used for automatic target recognition (ATR). We show how unconstrained networks are likely to give poor generalization on the ATR problem. We also show how the ATR problem requires a special type of classifier called a one-class classifier. The network constraints come in two forms: architectural constraints and learning constraints. Some of the constraints are used to improve generalization, while others are incorporated so that the network will be forced to perform one-class classification.

Paper Details

Date Published: 16 September 1992
PDF: 11 pages
Proc. SPIE 1709, Applications of Artificial Neural Networks III, (16 September 1992); doi: 10.1117/12.139976
Show Author Affiliations
Donald R. Hush, Univ. of New Mexico (United States)
Mary M. Moya, Sandia National Labs. (United States)
Shang-Ying Clark, Univ. of New Mexico (United States)

Published in SPIE Proceedings Vol. 1709:
Applications of Artificial Neural Networks III
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top