Fuzzy neural network model with three-layered structure

Chih Chia Yao, Yau-Hwang Kuo

研究成果: Paper

6 引文 (Scopus)

摘要

In this paper, a three-layered fuzzy neural network model is developed to execute parallel fuzzy inference with linguistic knowledge representation. Each linguistic variable and its linguistic term set is encapsulated into a single linguistic neuron, which may operate in normal mode or reverse mode. In normal mode, it has the functions of fuzzification and matching degree calculation. In reverse mode, it has the functions of evidence combination, conclusion making and defuzzification. In the three-layered model, the input (premise) layer is composed of a set of linguistic neurons operating in normal mode, while the output (conclusion) layer contains a set of linguistic neurons operating in reverse mode during inferencing but operating in normal mode during learning. Between the input layer and the output layer, a rule layer composed of rule neurons constitutes the truth-value flow channel from input layer to output layer in fuzzy inference. Each rule neuron represents a fuzzy rule. Such a three-layered structure makes a natural representation for fuzzy expert systems, and has faster inferencing and learning speed. This paper further developes a learning algorithm with the advantage of quick convergence. The learning algorithm includes a clustering phase before rule construction, whose results can provide useful information to construct rules by only building necessary links.

原文English
頁面1503-1510
頁數8
出版狀態Published - 1995 一月 1
事件Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5) - Yokohama, Jpn
持續時間: 1995 三月 201995 三月 24

Other

OtherProceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5)
城市Yokohama, Jpn
期間95-03-2095-03-24

指紋

Fuzzy neural networks
Fuzzy Neural Network
Neural Network Model
Linguistics
Neurons
Normal Modes
Neuron
Reverse
Fuzzy inference
Fuzzy Inference
Learning algorithms
Learning Algorithm
Output
Fuzzy Expert System
Defuzzification
Knowledge representation
Fuzzy rules
Linguistic Variables
Channel flow
Channel Flow

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

引用此文

Yao, C. C., & Kuo, Y-H. (1995). Fuzzy neural network model with three-layered structure. 1503-1510. 論文發表於 Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5), Yokohama, Jpn, .
Yao, Chih Chia ; Kuo, Yau-Hwang. / Fuzzy neural network model with three-layered structure. 論文發表於 Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5), Yokohama, Jpn, .8 p.
@conference{7183956d5bd54846b151ac199da71044,
title = "Fuzzy neural network model with three-layered structure",
abstract = "In this paper, a three-layered fuzzy neural network model is developed to execute parallel fuzzy inference with linguistic knowledge representation. Each linguistic variable and its linguistic term set is encapsulated into a single linguistic neuron, which may operate in normal mode or reverse mode. In normal mode, it has the functions of fuzzification and matching degree calculation. In reverse mode, it has the functions of evidence combination, conclusion making and defuzzification. In the three-layered model, the input (premise) layer is composed of a set of linguistic neurons operating in normal mode, while the output (conclusion) layer contains a set of linguistic neurons operating in reverse mode during inferencing but operating in normal mode during learning. Between the input layer and the output layer, a rule layer composed of rule neurons constitutes the truth-value flow channel from input layer to output layer in fuzzy inference. Each rule neuron represents a fuzzy rule. Such a three-layered structure makes a natural representation for fuzzy expert systems, and has faster inferencing and learning speed. This paper further developes a learning algorithm with the advantage of quick convergence. The learning algorithm includes a clustering phase before rule construction, whose results can provide useful information to construct rules by only building necessary links.",
author = "Yao, {Chih Chia} and Yau-Hwang Kuo",
year = "1995",
month = "1",
day = "1",
language = "English",
pages = "1503--1510",
note = "Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5) ; Conference date: 20-03-1995 Through 24-03-1995",

}

Yao, CC & Kuo, Y-H 1995, 'Fuzzy neural network model with three-layered structure', 論文發表於 Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5), Yokohama, Jpn, 95-03-20 - 95-03-24 頁 1503-1510.

Fuzzy neural network model with three-layered structure. / Yao, Chih Chia; Kuo, Yau-Hwang.

1995. 1503-1510 論文發表於 Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5), Yokohama, Jpn, .

研究成果: Paper

TY - CONF

T1 - Fuzzy neural network model with three-layered structure

AU - Yao, Chih Chia

AU - Kuo, Yau-Hwang

PY - 1995/1/1

Y1 - 1995/1/1

N2 - In this paper, a three-layered fuzzy neural network model is developed to execute parallel fuzzy inference with linguistic knowledge representation. Each linguistic variable and its linguistic term set is encapsulated into a single linguistic neuron, which may operate in normal mode or reverse mode. In normal mode, it has the functions of fuzzification and matching degree calculation. In reverse mode, it has the functions of evidence combination, conclusion making and defuzzification. In the three-layered model, the input (premise) layer is composed of a set of linguistic neurons operating in normal mode, while the output (conclusion) layer contains a set of linguistic neurons operating in reverse mode during inferencing but operating in normal mode during learning. Between the input layer and the output layer, a rule layer composed of rule neurons constitutes the truth-value flow channel from input layer to output layer in fuzzy inference. Each rule neuron represents a fuzzy rule. Such a three-layered structure makes a natural representation for fuzzy expert systems, and has faster inferencing and learning speed. This paper further developes a learning algorithm with the advantage of quick convergence. The learning algorithm includes a clustering phase before rule construction, whose results can provide useful information to construct rules by only building necessary links.

AB - In this paper, a three-layered fuzzy neural network model is developed to execute parallel fuzzy inference with linguistic knowledge representation. Each linguistic variable and its linguistic term set is encapsulated into a single linguistic neuron, which may operate in normal mode or reverse mode. In normal mode, it has the functions of fuzzification and matching degree calculation. In reverse mode, it has the functions of evidence combination, conclusion making and defuzzification. In the three-layered model, the input (premise) layer is composed of a set of linguistic neurons operating in normal mode, while the output (conclusion) layer contains a set of linguistic neurons operating in reverse mode during inferencing but operating in normal mode during learning. Between the input layer and the output layer, a rule layer composed of rule neurons constitutes the truth-value flow channel from input layer to output layer in fuzzy inference. Each rule neuron represents a fuzzy rule. Such a three-layered structure makes a natural representation for fuzzy expert systems, and has faster inferencing and learning speed. This paper further developes a learning algorithm with the advantage of quick convergence. The learning algorithm includes a clustering phase before rule construction, whose results can provide useful information to construct rules by only building necessary links.

UR - http://www.scopus.com/inward/record.url?scp=0029226958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029226958&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029226958

SP - 1503

EP - 1510

ER -

Yao CC, Kuo Y-H. Fuzzy neural network model with three-layered structure. 1995. 論文發表於 Proceedings of the 1995 IEEE International Conference on Fuzzy Systems. Part 1 (of 5), Yokohama, Jpn, .