Share Email Print

Proceedings Paper

Prototype selection rule for neural network training
Author(s): Lalit Gupta; Jiesheng Wang; Alain Mozart Charles; Paul Kisatsky
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

Rules to select a set of training prototypes from a collection of training prototypes are developed so that a neural network classifier converges to a solution when pattern classes overlap in feature space. The formulation of the selection rules are based on distortion measure and the network response to the training prototype collection. The rules are also especially useful for selecting training prototypes in order to improve the network robustness and operational flexibility by retraining the network with noisy prototypes. The application and effectiveness of the selection rules are demonstrated on a synthetic pattern classification in Gaussian noise problem and a practical automatic target recognition problem.

Paper Details

Date Published: 1 July 1992
PDF: 12 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140131
Show Author Affiliations
Lalit Gupta, Southern Illinois Univ./Carbondale (United States)
Jiesheng Wang, Southern Illinois Univ./Carbondale (United States)
Alain Mozart Charles, U.S. Army Armament Research, Development and Engineering Ctr. (United States)
Paul Kisatsky, U.S. Army Armament Research, Development and Engineering Ctr. (United States)

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

© SPIE. Terms of Use
Back to Top