skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Constrained neural network architectures for target recognition

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. 14 refs

Authors:
;  [1];  [2]
  1. New Mexico Univ., Albuquerque, NM (United States). Dept. of Electrical and Computer Engineering
  2. Sandia National Labs., Albuquerque, NM (United States)
Publication Date:
Research Org.:
Sandia National Labs., Albuquerque, NM (United States)
Sponsoring Org.:
USDOE; USDOE, Washington, DC (United States)
OSTI Identifier:
5693906
Report Number(s):
SAND-92-0648C; CONF-920471-3
ON: DE92011159
DOE Contract Number:  
AC04-76DP00789
Resource Type:
Conference
Resource Relation:
Conference: International Society for Photo Optical Engineering (SPIE) conference, Orlando, FL (United States), 20-24 Apr 1992
Country of Publication:
United States
Language:
English
Subject:
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; MILITARY EQUIPMENT; PATTERN RECOGNITION; NEURAL NETWORKS; ARTIFICIAL INTELLIGENCE; IMAGE PROCESSING; IMAGES; TARGETS; VEHICLES; EQUIPMENT; PROCESSING; 450000* - Military Technology, Weaponry, & National Defense; 990200 - Mathematics & Computers

Citation Formats

Hush, D R, Clark, Shang-Ying, and Moya, M M. Constrained neural network architectures for target recognition. United States: N. p., 1992. Web.
Hush, D R, Clark, Shang-Ying, & Moya, M M. Constrained neural network architectures for target recognition. United States.
Hush, D R, Clark, Shang-Ying, and Moya, M M. 1992. "Constrained neural network architectures for target recognition". United States.
@article{osti_5693906,
title = {Constrained neural network architectures for target recognition},
author = {Hush, D R and Clark, Shang-Ying and Moya, M M},
abstractNote = {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. 14 refs},
doi = {},
url = {https://www.osti.gov/biblio/5693906}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed Jan 01 00:00:00 EST 1992},
month = {Wed Jan 01 00:00:00 EST 1992}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: