A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

Original languageEnglish
Pages (from-to)1641-1646
Number of pages6
JournalIEEE Transactions on Neural Networks
Volume19
Issue number9
DOIs
Publication statusPublished - 12 Aug 2008

Fingerprint

Neural networks
Learning systems
Time series

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{80c6015205c04865b067281fd99af108,
title = "A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function",
abstract = "In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.",
author = "Yap, {Keem Siah} and Lim, {Chee Peng} and {Zainal Abidin}, Izham",
year = "2008",
month = "8",
day = "12",
doi = "10.1109/TNN.2008.2000992",
language = "English",
volume = "19",
pages = "1641--1646",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "9",

}

A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function. / Yap, Keem Siah; Lim, Chee Peng; Zainal Abidin, Izham.

In: IEEE Transactions on Neural Networks, Vol. 19, No. 9, 12.08.2008, p. 1641-1646.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function

AU - Yap, Keem Siah

AU - Lim, Chee Peng

AU - Zainal Abidin, Izham

PY - 2008/8/12

Y1 - 2008/8/12

N2 - In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

AB - In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

UR - http://www.scopus.com/inward/record.url?scp=52149111368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52149111368&partnerID=8YFLogxK

U2 - 10.1109/TNN.2008.2000992

DO - 10.1109/TNN.2008.2000992

M3 - Article

C2 - 18779094

AN - SCOPUS:52149111368

VL - 19

SP - 1641

EP - 1646

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 9

ER -