HYBRID NEURAL NETS CAN BE FUZZY CONTROLLERS AND FUZZY EXPERT-SYSTEMS

被引：21

作者：

BUCKLEY, JJ ^{[1
]}

HAYASHI, Y ^{[1
]}

机构：

[1] IBARAKI UNIV,DEPT COMP & INFORMAT SCI,HITACHI,IBARAKI 316,JAPAN

来源：

FUZZY SETS AND SYSTEMS | 1993年 / 60卷 / 02期

关键词：

NEURAL NETWORKS; FUZZY CONTROLLER; FUZZY EXPERT SYSTEMS; HYBRID NEURAL NETWORKS;

D O I：

10.1016/0165-0114(93)90342-F

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Given a discrete fuzzy expert system we show how to construct a hybrid neural net computationally identical to the fuzzy expert system. Given a Sugeno, Mamdani, or expert system type of controller we build a hybrid neural net that is computationally the same as the controller. This improves on previous results that show a (regular) neural net can approximate continuous fuzzy controllers and continuous fuzzy expert systems to any degree of accuracy.

引用

页码：135 / 142

页数：8

共 53 条

[1]

[Anonymous], 1992, NEURAL NETWORKS FUZZ

[2]

[Anonymous], 1991, INT J APPROX REASON, DOI DOI 10.1016/0888-613X(91)90008-A

[3] LEARNING AND TUNING FUZZY-LOGIC CONTROLLERS THROUGH REINFORCEMENTS [J].

BERENJI, HR ;

KHEDKAR, P .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05) :724-740

[4]

BERENJI HR, 1993, 2ND P IEEE C FUZZ SY, V2, P1395

[5] APPROXIMATION-THEORY AND FEEDFORWARD NETWORKS [J].

BLUM, EK ;

LI, LK .

NEURAL NETWORKS, 1991, 4 (04) :511-515

[6] EXPERT FUZZY CONTROLLER [J].

BUCKLEY, JJ ;

YING, H .

FUZZY SETS AND SYSTEMS, 1991, 44 (03) :373-390

[7] ON THE EQUIVALENCE OF NEURAL NETS AND FUZZY EXPERT SYSTEMS [J].

BUCKLEY, JJ ;

HAYASHI, Y ;

CZOGALA, E .

FUZZY SETS AND SYSTEMS, 1993, 53 (02) :129-134

[8] A FUZZY EXPERT SYSTEM [J].

BUCKLEY, JJ ;

SILER, W ;

TUCKER, D .

FUZZY SETS AND SYSTEMS, 1986, 20 (01) :1-16

[9] THEORY OF THE FUZZY CONTROLLER - AN INTRODUCTION [J].

BUCKLEY, JJ .

FUZZY SETS AND SYSTEMS, 1992, 51 (03) :249-258

[10]

BUCKLEY JJ, IN PRESS FUZZY SETS

← 1 2 3 4 5 6 →