Nonparametric training algorithm for decentralized binary hypothesis testing networks

John W Wissinger, Michael Athans

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a distributed nonparametric minimum-error training algorithm for networks of linear threshold classifiers performing decentralized binary hypothesis testing (detection). The training algorithm consists of communicating stochastic approximation algorithms. Knowledge of the network topology is required by the algorithm. We suggest that models of the variety in this study provide a paradigm for the study of adaptation in human decision making organizations.

Original languageEnglish (US)
Title of host publicationAmerican Control Conference
Editors Anon
PublisherPubl by IEEE
Pages176-177
Number of pages2
ISBN (Print)0780308611
StatePublished - 1993
Externally publishedYes
EventProceedings of the 1993 American Control Conference Part 3 (of 3) - San Francisco, CA, USA
Duration: Jun 2 1993Jun 4 1993

Other

OtherProceedings of the 1993 American Control Conference Part 3 (of 3)
CitySan Francisco, CA, USA
Period6/2/936/4/93

Fingerprint

Testing
Approximation algorithms
Classifiers
Decision making
Topology

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Wissinger, J. W., & Athans, M. (1993). Nonparametric training algorithm for decentralized binary hypothesis testing networks. In Anon (Ed.), American Control Conference (pp. 176-177). Publ by IEEE.

Nonparametric training algorithm for decentralized binary hypothesis testing networks. / Wissinger, John W; Athans, Michael.

American Control Conference. ed. / Anon. Publ by IEEE, 1993. p. 176-177.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wissinger, JW & Athans, M 1993, Nonparametric training algorithm for decentralized binary hypothesis testing networks. in Anon (ed.), American Control Conference. Publ by IEEE, pp. 176-177, Proceedings of the 1993 American Control Conference Part 3 (of 3), San Francisco, CA, USA, 6/2/93.
Wissinger JW, Athans M. Nonparametric training algorithm for decentralized binary hypothesis testing networks. In Anon, editor, American Control Conference. Publ by IEEE. 1993. p. 176-177
Wissinger, John W ; Athans, Michael. / Nonparametric training algorithm for decentralized binary hypothesis testing networks. American Control Conference. editor / Anon. Publ by IEEE, 1993. pp. 176-177
@inproceedings{c0a103b7d021460c8e4429a23a7e1ba5,
title = "Nonparametric training algorithm for decentralized binary hypothesis testing networks",
abstract = "We present a distributed nonparametric minimum-error training algorithm for networks of linear threshold classifiers performing decentralized binary hypothesis testing (detection). The training algorithm consists of communicating stochastic approximation algorithms. Knowledge of the network topology is required by the algorithm. We suggest that models of the variety in this study provide a paradigm for the study of adaptation in human decision making organizations.",
author = "Wissinger, {John W} and Michael Athans",
year = "1993",
language = "English (US)",
isbn = "0780308611",
pages = "176--177",
editor = "Anon",
booktitle = "American Control Conference",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Nonparametric training algorithm for decentralized binary hypothesis testing networks

AU - Wissinger, John W

AU - Athans, Michael

PY - 1993

Y1 - 1993

N2 - We present a distributed nonparametric minimum-error training algorithm for networks of linear threshold classifiers performing decentralized binary hypothesis testing (detection). The training algorithm consists of communicating stochastic approximation algorithms. Knowledge of the network topology is required by the algorithm. We suggest that models of the variety in this study provide a paradigm for the study of adaptation in human decision making organizations.

AB - We present a distributed nonparametric minimum-error training algorithm for networks of linear threshold classifiers performing decentralized binary hypothesis testing (detection). The training algorithm consists of communicating stochastic approximation algorithms. Knowledge of the network topology is required by the algorithm. We suggest that models of the variety in this study provide a paradigm for the study of adaptation in human decision making organizations.

UR - http://www.scopus.com/inward/record.url?scp=0027799651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027799651&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027799651

SN - 0780308611

SP - 176

EP - 177

BT - American Control Conference

A2 - Anon, null

PB - Publ by IEEE

ER -