APPROXIMATION CAPABILITIES OF MULTILAYER FEEDFORWARD REGULAR FUZZY NEURAL NETWORKS

被引：0
|
作者：
Liu PuyinDept. of Math.
Dept. of Math.
机构：
来源：
Applied Mathematics:A Journal of Chinese Universities | 2001年 / 01期
关键词：
Regular fuzzy neural networks; cut preserving fuzzy mappings; universal approximators; fuzzy valued Bernstein polynomials;
D O I：
暂无
中图分类号：
TP183 [人工神经网络与计算]; O159 [模糊数学];
学科分类号：
070104 ; 081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Four layer feedforward regular fuzzy neural networks are constructed. Universal approximations to some continuous fuzzy functions defined on F 0 (R) n by the four layer fuzzy neural networks are shown. At first,multivariate Bernstein polynomials associated with fuzzy valued functions are empolyed to approximate continuous fuzzy valued functions defined on each compact set of R n . Secondly,by introducing cut preserving fuzzy mapping,the equivalent conditions for continuous fuzzy functions that can be arbitrarily closely approximated by regular fuzzy neural networks are shown. Finally a few of sufficient and necessary conditions for characterizing approximation capabilities of regular fuzzy neural networks are obtained. And some concrete fuzzy functions demonstrate our conclusions.
引用
收藏
页码：45 / 57
页数：13
相关论文
共 50 条
12345