Conjunctoid learning and performance algorithms

R. J. Jannarone, K. F. Yu, Yoshiyasu Takefuji

Research output: Contribution to journalArticle

Abstract

In its first 40 years the neural network learning (NNL) movement has produced an impressive array of learning models. We introduce a general family of fast and efficient NNL learning modules for binary events called 'conjunctoids', which employ an appropriate framework from probability theory; adapt a class of recently developed conjunctive models from psychometric theory; tailor sound statistical estimation and evaluation schemes to fit NNL learning needs; and allow VLSI implementations.

Original languageEnglish
Pages (from-to)186
Number of pages1
JournalNeural Networks
Volume1
Issue number1 SUPPL
DOIs
Publication statusPublished - 1988
Externally publishedYes

Fingerprint

Learning
Neural networks
Probability Theory
Acoustic waves
Psychometrics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

Conjunctoid learning and performance algorithms. / Jannarone, R. J.; Yu, K. F.; Takefuji, Yoshiyasu.

In: Neural Networks, Vol. 1, No. 1 SUPPL, 1988, p. 186.

Research output: Contribution to journalArticle

Jannarone, R. J. ; Yu, K. F. ; Takefuji, Yoshiyasu. / Conjunctoid learning and performance algorithms. In: Neural Networks. 1988 ; Vol. 1, No. 1 SUPPL. pp. 186.
@article{fa5930bce2fd42ff82c68fe1ac9235e0,
title = "Conjunctoid learning and performance algorithms",
abstract = "In its first 40 years the neural network learning (NNL) movement has produced an impressive array of learning models. We introduce a general family of fast and efficient NNL learning modules for binary events called 'conjunctoids', which employ an appropriate framework from probability theory; adapt a class of recently developed conjunctive models from psychometric theory; tailor sound statistical estimation and evaluation schemes to fit NNL learning needs; and allow VLSI implementations.",
author = "Jannarone, {R. J.} and Yu, {K. F.} and Yoshiyasu Takefuji",
year = "1988",
doi = "10.1016/0893-6080(88)90223-7",
language = "English",
volume = "1",
pages = "186",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "1 SUPPL",

}

TY - JOUR

T1 - Conjunctoid learning and performance algorithms

AU - Jannarone, R. J.

AU - Yu, K. F.

AU - Takefuji, Yoshiyasu

PY - 1988

Y1 - 1988

N2 - In its first 40 years the neural network learning (NNL) movement has produced an impressive array of learning models. We introduce a general family of fast and efficient NNL learning modules for binary events called 'conjunctoids', which employ an appropriate framework from probability theory; adapt a class of recently developed conjunctive models from psychometric theory; tailor sound statistical estimation and evaluation schemes to fit NNL learning needs; and allow VLSI implementations.

AB - In its first 40 years the neural network learning (NNL) movement has produced an impressive array of learning models. We introduce a general family of fast and efficient NNL learning modules for binary events called 'conjunctoids', which employ an appropriate framework from probability theory; adapt a class of recently developed conjunctive models from psychometric theory; tailor sound statistical estimation and evaluation schemes to fit NNL learning needs; and allow VLSI implementations.

UR - http://www.scopus.com/inward/record.url?scp=0024167310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024167310&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90223-7

DO - 10.1016/0893-6080(88)90223-7

M3 - Article

VL - 1

SP - 186

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 1 SUPPL

ER -