STRUCTURE OPTIMIZATION OF FUZZY NEURAL-NETWORK BY GENETIC ALGORITHM

被引：95

作者：

ISHIGAMI, H ^{[1
]}

FUKUDA, T ^{[1
]}

SHIBATA, T ^{[1
]}

ARAI, F ^{[1
]}

机构：

[1] MINIST INT TRADE & IND,DEPT ROBOT,DIV BIOROBOT,MECH ENGN LAB,TSUKUBA,IBARAKI 305,JAPAN

来源：

FUZZY SETS AND SYSTEMS | 1995年 / 71卷 / 03期

关键词：

FUZZY INFERENCE; GENETIC ALGORITHM; LEARNING;

D O I：

10.1016/0165-0114(94)00283-D

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper presents an auto-tuning method of fuzzy inference using genetic algorithm and delta rule. Fuzzy inference is applied to various problems. However, the determination of membership functions of the fuzzy inference depends on human experts, which is a difficult problem and time-consuming. Therefore, some auto-tuning methods have been proposed to reduce the time-consuming operations. However, the convergence of the tuning by the conventional methods depends on the initial conditions of the fuzzy model. So, we propose an auto-tuning method for the fuzzy neural network by genetic algorithm. The new tuning method realizes to construct minimal and optimal structure of the fuzzy model. This paper shows effectiveness of the tuning system by simulations compared with the conventional method.

引用

页码：257 / 264

页数：8