Universal Approximation with Fuzzy ART and Fuzzy ARTMAP

Stephen J. Verzi; Gregory L. Heileman; Michael Georgiopoulos; Georgios C. Anagnostopoulos

Universal Approximation with Fuzzy ART and Fuzzy ARTMAP

Stephen J. Verzi, Gregory L. Heileman, Michael Georgiopoulos, Georgios C. Anagnostopoulos

Research output: Contribution to conference › Paper › peer-review

Abstract

A measure of success for any learning algorithm is how useful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically be applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we will provide a proof to show that Fuzzy ART augmented with a single layer of perceptrons is a universal approximator. Moreover, the Fuzzy ARTMAP neural network architecture, by itself, will be shown to be a universal approximator.

Original language	English (US)
Pages	1987-1992
Number of pages	6
State	Published - 2003
Externally published	Yes
Event	International Joint Conference on Neural Networks 2003 - Portland, OR, United States Duration: Jul 20 2003 → Jul 24 2003

Conference

Conference	International Joint Conference on Neural Networks 2003
Country/Territory	United States
City	Portland, OR
Period	7/20/03 → 7/24/03

Keywords

Adaptive Resonance Theory
Machine Learning
Neural Networks
Universal Function Approximation

ASJC Scopus subject areas

Software
Artificial Intelligence

Cite this

@conference{1560fc8aec6f444797906e11e0730592,

title = "Universal Approximation with Fuzzy ART and Fuzzy ARTMAP",

abstract = "A measure of success for any learning algorithm is how useful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically be applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we will provide a proof to show that Fuzzy ART augmented with a single layer of perceptrons is a universal approximator. Moreover, the Fuzzy ARTMAP neural network architecture, by itself, will be shown to be a universal approximator.",

keywords = "Adaptive Resonance Theory, Machine Learning, Neural Networks, Universal Function Approximation",

author = "Verzi, {Stephen J.} and Heileman, {Gregory L.} and Michael Georgiopoulos and Anagnostopoulos, {Georgios C.}",

year = "2003",

language = "English (US)",

pages = "1987--1992",

note = "International Joint Conference on Neural Networks 2003 ; Conference date: 20-07-2003 Through 24-07-2003",

}

TY - CONF

T1 - Universal Approximation with Fuzzy ART and Fuzzy ARTMAP

AU - Verzi, Stephen J.

AU - Heileman, Gregory L.

AU - Georgiopoulos, Michael

AU - Anagnostopoulos, Georgios C.

PY - 2003

Y1 - 2003

N2 - A measure of success for any learning algorithm is how useful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically be applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we will provide a proof to show that Fuzzy ART augmented with a single layer of perceptrons is a universal approximator. Moreover, the Fuzzy ARTMAP neural network architecture, by itself, will be shown to be a universal approximator.

AB - A measure of success for any learning algorithm is how useful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically be applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we will provide a proof to show that Fuzzy ART augmented with a single layer of perceptrons is a universal approximator. Moreover, the Fuzzy ARTMAP neural network architecture, by itself, will be shown to be a universal approximator.

KW - Adaptive Resonance Theory

KW - Machine Learning

KW - Neural Networks

KW - Universal Function Approximation

UR - http://www.scopus.com/inward/record.url?scp=0141682847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141682847&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0141682847

SP - 1987

EP - 1992

T2 - International Joint Conference on Neural Networks 2003

Y2 - 20 July 2003 through 24 July 2003

ER -

Universal Approximation with Fuzzy ART and Fuzzy ARTMAP

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this