Generalized fuzzy inference neural network using a self-organizing feature map

Hiroshi Kitajima, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

A new model for generalized fuzzy inference neural networks (GFINN) is proposed in this paper. The networks consist of three layers: an input-output layer, an if layer, and a then layer. In each layer, there are the operational nodes. A GFINN can perform three representative fuzzy inference methods by changing the connectivity and the operational nodes. There are three learning processes in a GFINN: a self-organizing process, a rule-integration process, and a LMS learning process. In the rule-integration process, a GFINN employs two feature maps in order to integrate appropriate rules effectively. Computer simulations were carried out to show the superiority of a GFINN over back-propagation networks.

Original languageEnglish
Pages (from-to)40-48
Number of pages9
JournalElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
Volume125
Issue number3
Publication statusPublished - 1998

Fingerprint

Self organizing maps
Fuzzy inference
Neural networks
Backpropagation
Computer simulation

Keywords

  • Fuzzy inference
  • Neural network
  • Operation node
  • Partition of input and output spaces
  • Self-organization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{b335029337e146ab8d8e30751c00bc30,
title = "Generalized fuzzy inference neural network using a self-organizing feature map",
abstract = "A new model for generalized fuzzy inference neural networks (GFINN) is proposed in this paper. The networks consist of three layers: an input-output layer, an if layer, and a then layer. In each layer, there are the operational nodes. A GFINN can perform three representative fuzzy inference methods by changing the connectivity and the operational nodes. There are three learning processes in a GFINN: a self-organizing process, a rule-integration process, and a LMS learning process. In the rule-integration process, a GFINN employs two feature maps in order to integrate appropriate rules effectively. Computer simulations were carried out to show the superiority of a GFINN over back-propagation networks.",
keywords = "Fuzzy inference, Neural network, Operation node, Partition of input and output spaces, Self-organization",
author = "Hiroshi Kitajima and Masafumi Hagiwara",
year = "1998",
language = "English",
volume = "125",
pages = "40--48",
journal = "Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)",
issn = "0424-7760",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - Generalized fuzzy inference neural network using a self-organizing feature map

AU - Kitajima, Hiroshi

AU - Hagiwara, Masafumi

PY - 1998

Y1 - 1998

N2 - A new model for generalized fuzzy inference neural networks (GFINN) is proposed in this paper. The networks consist of three layers: an input-output layer, an if layer, and a then layer. In each layer, there are the operational nodes. A GFINN can perform three representative fuzzy inference methods by changing the connectivity and the operational nodes. There are three learning processes in a GFINN: a self-organizing process, a rule-integration process, and a LMS learning process. In the rule-integration process, a GFINN employs two feature maps in order to integrate appropriate rules effectively. Computer simulations were carried out to show the superiority of a GFINN over back-propagation networks.

AB - A new model for generalized fuzzy inference neural networks (GFINN) is proposed in this paper. The networks consist of three layers: an input-output layer, an if layer, and a then layer. In each layer, there are the operational nodes. A GFINN can perform three representative fuzzy inference methods by changing the connectivity and the operational nodes. There are three learning processes in a GFINN: a self-organizing process, a rule-integration process, and a LMS learning process. In the rule-integration process, a GFINN employs two feature maps in order to integrate appropriate rules effectively. Computer simulations were carried out to show the superiority of a GFINN over back-propagation networks.

KW - Fuzzy inference

KW - Neural network

KW - Operation node

KW - Partition of input and output spaces

KW - Self-organization

UR - http://www.scopus.com/inward/record.url?scp=0032205049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032205049&partnerID=8YFLogxK

M3 - Article

VL - 125

SP - 40

EP - 48

JO - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

JF - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

SN - 0424-7760

IS - 3

ER -