Original contribution
Conjunctoids: Statistical learning modules for binary events

https://doi.org/10.1016/0893-6080(88)90006-8Get rights and content

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.

References (50)

  • F. Crick et al.

    Certain aspects of the anatomy and physiology of the cerebral cortex

  • P.A. Devijver et al.

    Pattern recognition: A statistical approach

    (1982)
  • N.R. Draper et al.

    Applied linear regression

    (1966)
  • J.A. Feldman

    A connectionist model of vision memory

  • J.A. Feldman

    Dynamic connections in neural networks

    Biological Cybernetics

    (1982)
  • T.S. Ferguson

    Mathematical statistics: A decision theoretic approach

    (1967)
  • M. Goldstein et al.

    Discrete discriminant analysis

    (1978)
  • S. Grossberg

    On learning and energy-entropy dependence in recurrent and nonrecurrent signed networks

    Journal of Statistical Physics

    (1969)
  • S. Grossberg

    Adaptive pattern classification and universal recoding, I: Parallel development and coding of neural feature detectors

    Biological Cybernetics

    (1976)
  • S. Grossberg

    Studies of mind and brain: Neural principles of learning, perception, development, cognition and motor control

    (1982)
  • S. Grossberg

    Nonlinear neural networks: Principles, mechanism, and architectures

    Neural Networks

    (1988)
  • G.E. Hinton et al.

    Learning and relearning in Boltzman machines

  • G.E. Hinton et al.

    Distributed representations

  • J.J. Hopfield et al.

    “Unlearning” has a stabilizing effect in collective memories

    Nature

    (1983)
  • R.J. Jannarone

    Conjunctive item response theory kernels

    Psychometrika

    (1986)
  • Cited by (5)

    This is an abridged version of a detailed report, which is available from the authors upon request.

    View full text