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

[11]

BUCKLEY JJ, 1992, CYBERNETICS APPLIED, P293

[12]

BUCKLEY JJ, IN PRESS ARCH THEORE

[13] APPROXIMATION OF A FUNCTION AND ITS DERIVATIVE WITH A NEURAL NETWORK [J].

CARDALIAGUET, P ;

EUVRARD, G .

NEURAL NETWORKS, 1992, 5 (02) :207-220

[14] THE CMAC AND A THEOREM OF KOLMOGOROV [J].

COTTER, NE ;

GUILLERM, TJ .

NEURAL NETWORKS, 1992, 5 (02) :221-228

[15]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[16]

DUBOIS D, 1988, FUZZY COMPUTING, P11

[17]

FREISLEBEN B, 1993, 2ND P IEEE INT C FUZ, V1, P321

[18] A CONSTRUCTIVE METHOD FOR MULTIVARIATE FUNCTION APPROXIMATION BY MULTILAYER PERCEPTRONS [J].

GEVA, S ;

SITTE, J .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (04) :621-624

[19]

Gupta M.M., 1985, APPROXIMATE REASONIN, P217

[20]

GUPTA MM, 1991, NOV P IEEE INT C NEU, V2, P1454

← 1 2 3 4 5 6 →