Pattern-recognition by an artificial network derived from biologic neuronal systems

D L Alkon; K T Blackwell; G S Barbour; A K Rigler; T P Vogl

doi:10.1007/BF00197642

Back

Pattern-recognition by an artificial network derived from biologic neuronal systems

Journal article

Peer reviewed

Pattern-recognition by an artificial network derived from biologic neuronal systems

D L Alkon, K T Blackwell, G S Barbour, A K Rigler and T P Vogl

Biological cybernetics, Vol.62(5), pp.363-376

01/01/1990

DOI: 10.1007/BF00197642

PMID: 2331490

View Online

Abstract

A novel artificial neural network, derived from neurobiological observations, is described and examples of its performance are presented. This DYnamically STable Associative Learning (DYSTAL) network associatively learns both correlations and anticorrelations, and can be configured to classify or restore patterns with only a change in the number of output units. DYSTAL exhibits some particularly desirable properties: computational effort scales linearly with the number of connections, i.e., it is O(N) in complexity; performance of the network is stable with respect to network parameters over wide ranges of their values and over the size of the input field; storage of a very large number of patterns is possible; patterns need not be orthogonal; network connections are not restricted to multi-layer feed-forward or any other specific structure; and, for a known set of deterministic input patterns, the network weights can be computed, a priori, in closed form. The network has been associatively trained to perform the XOR function as well as other classification tasks. The network has also been trained to restore patterns obscured by binary or analog noise. Neither global nor local feedback connections are required during learning; hence the network is particularly suitable for hardware (VLSI) implementation.

Animals

Models, Neurological

Nerve Net - physiology

Nervous System Physiological Phenomena

Pattern Recognition, Automated

Rabbits

Details

Title: Subtitle: Pattern-recognition by an artificial network derived from biologic neuronal systems
Creators: D L Alkon - National Institutes of Health
K T Blackwell - Environmental Research Institute of Michigan
G S Barbour - Environmental Research Institute of Michigan
A K Rigler - Missouri University of Science and Technology
T P Vogl - Environmental Research Institute of Michigan
Resource Type: Journal article
Publication Details: Biological cybernetics, Vol.62(5), pp.363-376
DOI: 10.1007/BF00197642
PMID: 2331490
NLM abbreviation: Biol Cybern
ISSN: 0340-1200
eISSN: 1432-0770
Language: English
Date published: 01/01/1990
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute
Record Identifier: 9984446458202771

Metrics

5 Record Views

33 Times Cited - Web of Science

See more details