Neuro-fuzzy relational systems for nonlinear approximation and prediction

被引：29

作者：

Scherer, Rafal ^{[1
]}

机构：

[1] Czestochowa Tech Univ, Dept Comp Engn, PL-42200 Czestochowa, Poland

来源：

NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS | 2009年 / 71卷 / 12期

关键词：

Fuzzy logic; Neuro-fuzzy systems; Machine learning;

D O I：

10.1016/j.na.2009.01.180

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

There are many machine learning systems developed so far. Fuzzy systems along with neural network are the most commonly used learning systems. Researchers mainly use Mamdani (linguistic) and Takagi Sugeno fuzzy systems, and in the paper, relational neuro-fuzzy systems are proposed for better flexibility. Linguistic systems store an input-output mapping in the form of fuzzy IF-THEN rules with linguistic terms both in antecedents and consequents. Relational fuzzy systems bond input and output fuzzy linguistic values by a binary relation thus fuzzy rules have additional weights. Thanks to this the system is better adjustable to learning data. Described systems are tested on several known benchmarks and compared with other machine learning solutions from the literature. (C) 2009 Elsevier Ltd. All rights reserved.

引用

页码：E1420 / E1425

页数：6

共 19 条

[1]

[Anonymous], 1997, FUZZY NEURAL NETWORK

[2]

Asuncion Arthur, 2007, Uci machine learning repository

[3]

Bezdek J., 1999, FUZZY MODELS ALGORIT

[4]

Bezdek JC., 1992, FUZZY MODELS PATTERN