ON THE EQUIVALENCE OF NEURAL NETS AND FUZZY EXPERT SYSTEMS

被引：44
作者：
BUCKLEY, JJ
HAYASHI, Y
CZOGALA, E
机构：
[1] IBARAKI UNIV,DEPT COMP & INFORMAT SCI,IBARAKI 316,JAPAN
[2] TECH UNIV SILESIA,DEPT AUTOMAT CONTROL ELECTR & COMP SCI,PL-44101 GLIWICE,POLAND
来源：
FUZZY SETS AND SYSTEMS | 1993年 / 53卷 / 02期
关键词：
FUZZY EXPERT SYSTEMS; NEURAL NETS; APPROXIMATION; DISCRETIZATION; CONTINUOUS SYSTEMS;
D O I：
10.1016/0165-0114(93)90167-G
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
We show, under the assumptions described in the paper, that: (1) we can approximate a neural net to any degree of accuracy using a fuzzy expert system; and conversely (2) we may approximate a fuzzy expert system to any degree of accuracy with a neural net.
引用
收藏
页码：129 / 134
页数：6
相关论文
共 12 条
[1]   APPROXIMATION-THEORY AND FEEDFORWARD NETWORKS [J].
BLUM, EK ;
LI, LK .
NEURAL NETWORKS, 1991, 4 (04) :511-515
[2]  
BUCKLEY JJ, 1993, IN PRESS FUZZY SETS, V53
[3]  
BUCKLEY JJ, IN PRESS AUTOMATICA
[4]  
Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274
[5]   APPROXIMATION CAPABILITIES OF MULTILAYER FEEDFORWARD NETWORKS [J].
HORNIK, K .
NEURAL NETWORKS, 1991, 4 (02) :251-257
[6]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[7]  
Kandel A., 1986, FUZZY MATH TECHNIQUE
[8]  
Kandel A., 1991, FUZZY EXPERT SYSTEMS
[9]   ARBITRARY NONLINEARITY IS SUFFICIENT TO REPRESENT ALL FUNCTIONS BY NEURAL NETWORKS - A THEOREM [J].
KREINOVICH, VY .
NEURAL NETWORKS, 1991, 4 (03) :381-383
[10]   FUZZY MODUS PONENS - A NEW MODEL SUITABLE FOR APPLICATIONS IN KNOWLEDGE-BASED SYSTEMS [J].
MAGREZ, P ;
SMETS, P .
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 1989, 4 (02) :181-200
12