IDENTIFICATION OF FUZZY RELATIONAL EQUATIONS BY FUZZY NEURAL NETWORKS

被引：36

作者：

BLANCO, A

DELGADO, M

REQUENA, I

机构：

[1] Departamento de Ciencias de la Computación e Inteligencia Artificial, la Universidad de Granada, Facultad de Ciencias

来源：

FUZZY SETS AND SYSTEMS | 1995年 / 71卷 / 02期

关键词：

NEURAL NETWORK; SMOOTH DERIVATIVE; MAX-MIN COMPOSITION;

D O I：

10.1016/0165-0114(94)00251-2

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Although the identification of a fuzzy system by a feedforward neural network is obviously possible, whenever the system was continuous, however when we use fuzzy max-min neural network, some problems on the learning of the network arise. In this paper we present a method to identify a fuzzy relation by a fuzzy max-min neural network. We adapt the learning algorithm backpropagation to learning of max-min neural network by using one which we will denote as ''smooth derivative''. Finally, we present some examples and a comparison with a similar method.

引用

页码：215 / 226

页数：12

共 13 条

[1]

BLANCO A, 1994, 3RD P IEEE INT C FUZ, P1737

[2]

BOUR L, 1988, BUSEFAL, V34, P86

[3]

BOUR L, 1986, BUSEFAL, V25, P95

[4]

CZOGALA E, 1982, FUZZY SETS SYSTEMS, V7, P275

[5]

DINOLA A, 1984, STOCHASTICA, V2, P99

[6]

DRAPER N, 1966, APPLIED REGRESSION A

[7]

DUBOIS G, 1992, P IEEE INT C FUZZ SE, P679

[8] ESTIMATION OF FUZZY RELATIONAL MATRIX BY USING PROBABILISTIC DESCENT METHOD [J].

IKOMA, N ;

PEDRYCZ, W ;

HIROTA, K .

FUZZY SETS AND SYSTEMS, 1993, 57 (03) :335-349

[9]

PEDRYCZ W, 1990, P INT C FUZZ LOG NEU, P235

[10]

SAITO T, 1991, 2ND P INT C FUZZ LOG, P184

← 1 2 →