APPROXIMATION ANALYSES FOR FUZZY VALUED FUNCTIONS IN L1（μ）-NORM BY REGULAR FUZZY NEURAL NETWORKS

被引：4
|
作者：
Liu Puyin (Dept. of System Eng. and Math.
机构：
来源：
Journal of Electronics(China) | 2000年 / 02期
基金：
中国国家自然科学基金;
关键词：
Fuzzy valued simple function; Regular fuzzy neural network; L1(μ) approximation; Universal approximator;
D O I：
暂无
中图分类号：
TP183 [人工神经网络与计算];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
By defining fuzzy valued simple functions and giving L1(μ) approximations of fuzzy valued integrably bounded functions by such simple functions, the paper analyses by L1(μ)-norm the approximation capability of four-layer feedforward regular fuzzy neural networks to the fuzzy valued integrably bounded function F : Rn → FcO(R). That is, if the transfer functionσ: R→R is non-polynomial and integrable function on each finite interval, F may be innorm approximated by fuzzy valued functions defined as to anydegree of accuracy. Finally some real examples demonstrate the conclusions.
引用
收藏
页码：132 / 138
页数：7
相关论文
共 50 条
12345