Dynamic control of an artificial neural system: The property inheritance network

Thomas W. Ryan, C Larrabee Winter, Charles J. Turner

Research output: Contribution to journalArticle

Abstract

The property inheritance network (PIN) is a dynamically controlled machine that accesses information stored in a hierarchical content addressable memory. The associative memory is implemented using adaptive resonance circuits. These circuits are monitored by a set of control neurons that become active when certain system states occur and generate signals that control a sequential search through a taxonomy of stored information. This paper reviews pertinent knowledge representation concepts and summarizes the adaptive resonance theory of Carpenter and Grossberg as it applies to the PIN. The PIN architecture and control implementation are presented and simulation results are discussed.

Original languageEnglish (US)
Pages (from-to)4972-4978
Number of pages7
JournalApplied Optics
Volume26
Issue number23
DOIs
StatePublished - 1987
Externally publishedYes

Fingerprint

dynamic control
associative memory
Circuit resonance
knowledge representation
Associative storage
taxonomy
Knowledge representation
Taxonomies
Network architecture
neurons
Neurons
Data storage equipment
Networks (circuits)
simulation

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Dynamic control of an artificial neural system : The property inheritance network. / Ryan, Thomas W.; Winter, C Larrabee; Turner, Charles J.

In: Applied Optics, Vol. 26, No. 23, 1987, p. 4972-4978.

Research output: Contribution to journalArticle

Ryan, Thomas W. ; Winter, C Larrabee ; Turner, Charles J. / Dynamic control of an artificial neural system : The property inheritance network. In: Applied Optics. 1987 ; Vol. 26, No. 23. pp. 4972-4978.
@article{a9d7fe1b46e341628105182023d88aa9,
title = "Dynamic control of an artificial neural system: The property inheritance network",
abstract = "The property inheritance network (PIN) is a dynamically controlled machine that accesses information stored in a hierarchical content addressable memory. The associative memory is implemented using adaptive resonance circuits. These circuits are monitored by a set of control neurons that become active when certain system states occur and generate signals that control a sequential search through a taxonomy of stored information. This paper reviews pertinent knowledge representation concepts and summarizes the adaptive resonance theory of Carpenter and Grossberg as it applies to the PIN. The PIN architecture and control implementation are presented and simulation results are discussed.",
author = "Ryan, {Thomas W.} and Winter, {C Larrabee} and Turner, {Charles J.}",
year = "1987",
doi = "10.1364/AO.26.004961",
language = "English (US)",
volume = "26",
pages = "4972--4978",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "23",

}

TY - JOUR

T1 - Dynamic control of an artificial neural system

T2 - The property inheritance network

AU - Ryan, Thomas W.

AU - Winter, C Larrabee

AU - Turner, Charles J.

PY - 1987

Y1 - 1987

N2 - The property inheritance network (PIN) is a dynamically controlled machine that accesses information stored in a hierarchical content addressable memory. The associative memory is implemented using adaptive resonance circuits. These circuits are monitored by a set of control neurons that become active when certain system states occur and generate signals that control a sequential search through a taxonomy of stored information. This paper reviews pertinent knowledge representation concepts and summarizes the adaptive resonance theory of Carpenter and Grossberg as it applies to the PIN. The PIN architecture and control implementation are presented and simulation results are discussed.

AB - The property inheritance network (PIN) is a dynamically controlled machine that accesses information stored in a hierarchical content addressable memory. The associative memory is implemented using adaptive resonance circuits. These circuits are monitored by a set of control neurons that become active when certain system states occur and generate signals that control a sequential search through a taxonomy of stored information. This paper reviews pertinent knowledge representation concepts and summarizes the adaptive resonance theory of Carpenter and Grossberg as it applies to the PIN. The PIN architecture and control implementation are presented and simulation results are discussed.

UR - http://www.scopus.com/inward/record.url?scp=84975542845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975542845&partnerID=8YFLogxK

U2 - 10.1364/AO.26.004961

DO - 10.1364/AO.26.004961

M3 - Article

AN - SCOPUS:84975542845

VL - 26

SP - 4972

EP - 4978

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 23

ER -