A fuzzy rule-based neural network model for revising approximate domain knowledge

Author

Lee, Hahn-Ming ; Lu, Bing-Hui

Author_Institution

Dept. of Electron. Eng., Nat. Taiwan Inst. of Technol., Taipei, Taiwan

Volume

1

fYear

1994

fDate

2-5 Oct 1994

Firstpage

634

Abstract

In this paper, a knowledge-based fuzzy neural network model, named KBFNN, is proposed. The initial structure of KBFNN can be constructed by approximate fuzzy rules. These approximate fuzzy rules may be incorrect or incomplete. Then, the approximate fuzzy rules are revised by neural network learning. Also, the fuzzy rules can be extracted from a revised KBFNN. To construct KBFNN by fuzzy rules, two kinds of fuzzy neurons are proposed. They are S-neurons and G-neurons. Besides, the KBFNN is capable of fuzzy inference. For processing fuzzy number efficiently, the LR-type fuzzy numbers are used. In a sample example, a knowledge-based evaluator (KBE) is demonstrated. The experimental results are very encouraging

Keywords

fuzzy neural nets; fuzzy set theory; inference mechanisms; knowledge based systems; G-neurons; KBFNN; LR-type fuzzy numbers; S-neurons; approximate domain knowledge revision; approximate fuzzy rules; fuzzy neurons; fuzzy rule-based neural network model; knowledge-based evaluator; knowledge-based fuzzy neural network model; Artificial neural networks; Electronic mail; Expert systems; Fuzzy neural networks; Fuzzy set theory; Information processing; Knowledge acquisition; Knowledge engineering; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-2129-4

Type

conf

DOI

10.1109/ICSMC.1994.399911

Filename

399911