Adaptive fuzzy inference neural network

Hitoshi Iyatomi, Masafumi Hagiwara

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.

Original languageEnglish
Pages (from-to)2049-2057
Number of pages9
JournalPattern Recognition
Volume37
Issue number10
DOIs
Publication statusPublished - 2004 Oct

Fingerprint

Fuzzy inference
Neural networks
Parameter estimation
Fuzzy systems
Identification (control systems)

Keywords

  • Fuzzy inference
  • Fuzzy modeling and rule extraction
  • Machine learning
  • Neural network

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Adaptive fuzzy inference neural network. / Iyatomi, Hitoshi; Hagiwara, Masafumi.

In: Pattern Recognition, Vol. 37, No. 10, 10.2004, p. 2049-2057.

Research output: Contribution to journalArticle

Iyatomi, Hitoshi ; Hagiwara, Masafumi. / Adaptive fuzzy inference neural network. In: Pattern Recognition. 2004 ; Vol. 37, No. 10. pp. 2049-2057.
@article{8f88d1b6d0ae4929b205d6ed4ef42c26,
title = "Adaptive fuzzy inference neural network",
abstract = "An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.",
keywords = "Fuzzy inference, Fuzzy modeling and rule extraction, Machine learning, Neural network",
author = "Hitoshi Iyatomi and Masafumi Hagiwara",
year = "2004",
month = "10",
doi = "10.1016/j.patcog.2004.04.003",
language = "English",
volume = "37",
pages = "2049--2057",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "10",

}

TY - JOUR

T1 - Adaptive fuzzy inference neural network

AU - Iyatomi, Hitoshi

AU - Hagiwara, Masafumi

PY - 2004/10

Y1 - 2004/10

N2 - An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.

AB - An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.

KW - Fuzzy inference

KW - Fuzzy modeling and rule extraction

KW - Machine learning

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=4544268143&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544268143&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2004.04.003

DO - 10.1016/j.patcog.2004.04.003

M3 - Article

AN - SCOPUS:4544268143

VL - 37

SP - 2049

EP - 2057

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 10

ER -