An efficient mapping of fuzzy ART onto a neural architecture

Matthias Blume, Sadik Esener

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

A novel mapping of the Fuzzy ART algorithm onto a neural network architecture is described. The architecture does not utilize bi-directional synapses, weight transport, or weight duplication, and requires one fewer layer of processing elements than the architecture originally proposed by Carpenter et al. (1991a). In the new architecture, execution of the algorithm takes a constant time per input vector regardless of the relationship between the input and existing templates, and several control signals are eliminated. This mapping facilitates hardware implementation of Fuzzy ART and furthermore serves as a tool for envisioning and understanding the algorithm.

Original languageEnglish (US)
Pages (from-to)409-411
Number of pages3
JournalNeural Networks
Volume10
Issue number3
DOIs
StatePublished - Apr 1997
Externally publishedYes

Fingerprint

Weights and Measures
Network architecture
Synapses
Neural networks
Hardware
Processing

Keywords

  • fuzzy ART
  • fuzzy ARTMAP
  • neural architecture
  • parallel hardware

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

An efficient mapping of fuzzy ART onto a neural architecture. / Blume, Matthias; Esener, Sadik.

In: Neural Networks, Vol. 10, No. 3, 04.1997, p. 409-411.

Research output: Contribution to journalArticle

Blume, Matthias ; Esener, Sadik. / An efficient mapping of fuzzy ART onto a neural architecture. In: Neural Networks. 1997 ; Vol. 10, No. 3. pp. 409-411.
@article{184b8b56c7d84e4dbf6b9925c818fad1,
title = "An efficient mapping of fuzzy ART onto a neural architecture",
abstract = "A novel mapping of the Fuzzy ART algorithm onto a neural network architecture is described. The architecture does not utilize bi-directional synapses, weight transport, or weight duplication, and requires one fewer layer of processing elements than the architecture originally proposed by Carpenter et al. (1991a). In the new architecture, execution of the algorithm takes a constant time per input vector regardless of the relationship between the input and existing templates, and several control signals are eliminated. This mapping facilitates hardware implementation of Fuzzy ART and furthermore serves as a tool for envisioning and understanding the algorithm.",
keywords = "fuzzy ART, fuzzy ARTMAP, neural architecture, parallel hardware",
author = "Matthias Blume and Sadik Esener",
year = "1997",
month = "4",
doi = "10.1016/S0893-6080(96)00085-8",
language = "English (US)",
volume = "10",
pages = "409--411",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - An efficient mapping of fuzzy ART onto a neural architecture

AU - Blume, Matthias

AU - Esener, Sadik

PY - 1997/4

Y1 - 1997/4

N2 - A novel mapping of the Fuzzy ART algorithm onto a neural network architecture is described. The architecture does not utilize bi-directional synapses, weight transport, or weight duplication, and requires one fewer layer of processing elements than the architecture originally proposed by Carpenter et al. (1991a). In the new architecture, execution of the algorithm takes a constant time per input vector regardless of the relationship between the input and existing templates, and several control signals are eliminated. This mapping facilitates hardware implementation of Fuzzy ART and furthermore serves as a tool for envisioning and understanding the algorithm.

AB - A novel mapping of the Fuzzy ART algorithm onto a neural network architecture is described. The architecture does not utilize bi-directional synapses, weight transport, or weight duplication, and requires one fewer layer of processing elements than the architecture originally proposed by Carpenter et al. (1991a). In the new architecture, execution of the algorithm takes a constant time per input vector regardless of the relationship between the input and existing templates, and several control signals are eliminated. This mapping facilitates hardware implementation of Fuzzy ART and furthermore serves as a tool for envisioning and understanding the algorithm.

KW - fuzzy ART

KW - fuzzy ARTMAP

KW - neural architecture

KW - parallel hardware

UR - http://www.scopus.com/inward/record.url?scp=0031127318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031127318&partnerID=8YFLogxK

U2 - 10.1016/S0893-6080(96)00085-8

DO - 10.1016/S0893-6080(96)00085-8

M3 - Article

AN - SCOPUS:0031127318

VL - 10

SP - 409

EP - 411

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 3

ER -