APPROXIMATIONS BETWEEN FUZZY EXPERT-SYSTEMS AND NEURAL NETWORKS

Authors
HAYASHI Y BUCKLEY JJ
Citation
Y. Hayashi et Jj. Buckley, APPROXIMATIONS BETWEEN FUZZY EXPERT-SYSTEMS AND NEURAL NETWORKS, International journal of approximate reasoning, 10(1), 1994, pp. 63-73
Citations number
28
Categorie Soggetti
Computer Sciences","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
International journal of approximate reasoning → ACNP
ISSN journal
0888613X
Volume
10
Issue
1
Year of publication
1994
Pages
63 - 73
Database
ISI
SICI code
0888-613X(1994)10:1<63:ABFEAN>2.0.ZU;2-Z
Abstract
The fuzzy expert system we are concerned about in this paper is a rule -based fuzzy expert system using any method of approximate reasoning t o evaluate the rules when given new data. In this paper we argue that: (1) any continuous fuzzy expert system may be approximated by a neura l net; and (2) any continuous neural net (feedforward multilayered) ma y be approximated by a fuzzy expert system. We show how to train the n eural net and how to write down the rules in the fuzzy expert system.