Conjunctoids: Statistical learning modules for binary events

Robert J. Jannarone, Kai F. Yu, Yoshiyasu Takefuji

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A general family of fast and efficient neural network learning modules for binary events is introduced. The family subsumes probabilistic as well as functional event associations; subsumes all levels of input/output association; yields truly parallel learning processes; provides for optimal parameter estimation; points toward a workable description of optimal model performance; and yields procedures that are simple and fast enough to be serious candidates for reflecting both neural functioning and real time machine learning. Examples as well as operational details are provided.

Original languageEnglish
Pages (from-to)325-337
Number of pages13
JournalNeural Networks
Volume1
Issue number4
DOIs
Publication statusPublished - 1988
Externally publishedYes

Fingerprint

Parameter estimation
Learning systems
Learning
Neural networks
Machine Learning

Keywords

  • Binary neural networks
  • Conjunctive measurement
  • Machine learning
  • Neurocomputing
  • Nonlinear neural networks
  • Parallel distributed processing
  • Statistical pattern recognition

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

Conjunctoids : Statistical learning modules for binary events. / Jannarone, Robert J.; Yu, Kai F.; Takefuji, Yoshiyasu.

In: Neural Networks, Vol. 1, No. 4, 1988, p. 325-337.

Research output: Contribution to journalArticle

Jannarone, Robert J. ; Yu, Kai F. ; Takefuji, Yoshiyasu. / Conjunctoids : Statistical learning modules for binary events. In: Neural Networks. 1988 ; Vol. 1, No. 4. pp. 325-337.
@article{41e4fb652e31422ab96d7b3737d1e6ac,
title = "Conjunctoids: Statistical learning modules for binary events",
abstract = "A general family of fast and efficient neural network learning modules for binary events is introduced. The family subsumes probabilistic as well as functional event associations; subsumes all levels of input/output association; yields truly parallel learning processes; provides for optimal parameter estimation; points toward a workable description of optimal model performance; and yields procedures that are simple and fast enough to be serious candidates for reflecting both neural functioning and real time machine learning. Examples as well as operational details are provided.",
keywords = "Binary neural networks, Conjunctive measurement, Machine learning, Neurocomputing, Nonlinear neural networks, Parallel distributed processing, Statistical pattern recognition",
author = "Jannarone, {Robert J.} and Yu, {Kai F.} and Yoshiyasu Takefuji",
year = "1988",
doi = "10.1016/0893-6080(88)90006-8",
language = "English",
volume = "1",
pages = "325--337",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Conjunctoids

T2 - Statistical learning modules for binary events

AU - Jannarone, Robert J.

AU - Yu, Kai F.

AU - Takefuji, Yoshiyasu

PY - 1988

Y1 - 1988

N2 - A general family of fast and efficient neural network learning modules for binary events is introduced. The family subsumes probabilistic as well as functional event associations; subsumes all levels of input/output association; yields truly parallel learning processes; provides for optimal parameter estimation; points toward a workable description of optimal model performance; and yields procedures that are simple and fast enough to be serious candidates for reflecting both neural functioning and real time machine learning. Examples as well as operational details are provided.

AB - A general family of fast and efficient neural network learning modules for binary events is introduced. The family subsumes probabilistic as well as functional event associations; subsumes all levels of input/output association; yields truly parallel learning processes; provides for optimal parameter estimation; points toward a workable description of optimal model performance; and yields procedures that are simple and fast enough to be serious candidates for reflecting both neural functioning and real time machine learning. Examples as well as operational details are provided.

KW - Binary neural networks

KW - Conjunctive measurement

KW - Machine learning

KW - Neurocomputing

KW - Nonlinear neural networks

KW - Parallel distributed processing

KW - Statistical pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=0024128210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024128210&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90006-8

DO - 10.1016/0893-6080(88)90006-8

M3 - Article

AN - SCOPUS:0024128210

VL - 1

SP - 325

EP - 337

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 4

ER -