Properties of learning of a Fuzzy ART Variant

M. Georgiopoulos; I. Dagher; G. L. Heileman; G. Bebis

doi:10.1016/S0893-6080(99)00031-3

Properties of learning of a Fuzzy ART Variant

M. Georgiopoulos, I. Dagher, G. L. Heileman, G. Bebis

Research output: Contribution to journal › Article › peer-review

31 Scopus citations

Abstract

This paper discusses a variation of the Fuzzy ART algorithm referred to as the Fuzzy ART Variant. The Fuzzy ART Variant is a Fuzzy ART algorithm that uses a very large choice parameter value. Based on the geometrical interpretation of the weights in Fuzzy ART, useful properties of learning associated with the Fuzzy ART Variant are presented and proven. One of these properties establishes an upper bound on the number of list presentations required by the Fuzzy ART Variant to learn an arbitrary list of input patterns. This bound is small and demonstrates the short-training time property of the Fuzzy ART Variant. Through simulation, it is shown that the Fuzzy ART Variant is as good a clustering algorithm as a Fuzzy ART algorithm that uses typical (i.e. small) values for the choice parameter. Copyright (C) 1999 Elsevier Science Ltd.

Original language	English (US)
Pages (from-to)	837-850
Number of pages	14
Journal	Neural Networks
Volume	12
Issue number	6
DOIs	https://doi.org/10.1016/S0893-6080(99)00031-3
State	Published - Jul 1999
Externally published	Yes

Keywords

Adaptive resonance theory
Clustering
Neural network
Supervised learning
Unsupervised learning

ASJC Scopus subject areas

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/S0893-6080(99)00031-3

Cite this

@article{d9f67b71ddf1427698b88b63fc221b95,

title = "Properties of learning of a Fuzzy ART Variant",

abstract = "This paper discusses a variation of the Fuzzy ART algorithm referred to as the Fuzzy ART Variant. The Fuzzy ART Variant is a Fuzzy ART algorithm that uses a very large choice parameter value. Based on the geometrical interpretation of the weights in Fuzzy ART, useful properties of learning associated with the Fuzzy ART Variant are presented and proven. One of these properties establishes an upper bound on the number of list presentations required by the Fuzzy ART Variant to learn an arbitrary list of input patterns. This bound is small and demonstrates the short-training time property of the Fuzzy ART Variant. Through simulation, it is shown that the Fuzzy ART Variant is as good a clustering algorithm as a Fuzzy ART algorithm that uses typical (i.e. small) values for the choice parameter. Copyright (C) 1999 Elsevier Science Ltd.",

keywords = "Adaptive resonance theory, Clustering, Neural network, Supervised learning, Unsupervised learning",

author = "M. Georgiopoulos and I. Dagher and Heileman, {G. L.} and G. Bebis",

note = "Funding Information: This research was supported in part by a grant from Boeing Computer Services under contract W-300445.",

year = "1999",

month = jul,

doi = "10.1016/S0893-6080(99)00031-3",

language = "English (US)",

volume = "12",

pages = "837--850",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd",

number = "6",

}

TY - JOUR

T1 - Properties of learning of a Fuzzy ART Variant

AU - Georgiopoulos, M.

AU - Dagher, I.

AU - Heileman, G. L.

AU - Bebis, G.

N1 - Funding Information: This research was supported in part by a grant from Boeing Computer Services under contract W-300445.

PY - 1999/7

Y1 - 1999/7

N2 - This paper discusses a variation of the Fuzzy ART algorithm referred to as the Fuzzy ART Variant. The Fuzzy ART Variant is a Fuzzy ART algorithm that uses a very large choice parameter value. Based on the geometrical interpretation of the weights in Fuzzy ART, useful properties of learning associated with the Fuzzy ART Variant are presented and proven. One of these properties establishes an upper bound on the number of list presentations required by the Fuzzy ART Variant to learn an arbitrary list of input patterns. This bound is small and demonstrates the short-training time property of the Fuzzy ART Variant. Through simulation, it is shown that the Fuzzy ART Variant is as good a clustering algorithm as a Fuzzy ART algorithm that uses typical (i.e. small) values for the choice parameter. Copyright (C) 1999 Elsevier Science Ltd.

AB - This paper discusses a variation of the Fuzzy ART algorithm referred to as the Fuzzy ART Variant. The Fuzzy ART Variant is a Fuzzy ART algorithm that uses a very large choice parameter value. Based on the geometrical interpretation of the weights in Fuzzy ART, useful properties of learning associated with the Fuzzy ART Variant are presented and proven. One of these properties establishes an upper bound on the number of list presentations required by the Fuzzy ART Variant to learn an arbitrary list of input patterns. This bound is small and demonstrates the short-training time property of the Fuzzy ART Variant. Through simulation, it is shown that the Fuzzy ART Variant is as good a clustering algorithm as a Fuzzy ART algorithm that uses typical (i.e. small) values for the choice parameter. Copyright (C) 1999 Elsevier Science Ltd.

KW - Adaptive resonance theory

KW - Clustering

KW - Neural network

KW - Supervised learning

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=0032797396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032797396&partnerID=8YFLogxK

U2 - 10.1016/S0893-6080(99)00031-3

DO - 10.1016/S0893-6080(99)00031-3

M3 - Article

AN - SCOPUS:0032797396

SN - 0893-6080

VL - 12

SP - 837

EP - 850

JO - Neural Networks

JF - Neural Networks

IS - 6

ER -

Properties of learning of a Fuzzy ART Variant

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this