Approximation capability of regular fuzzy neural networks to continuous fuzzy functions

被引:5
|
作者
Liu, PY [1 ]
Wang, H [1 ]
机构
[1] Natl Univ Def Technol, Dept Syst Engn & Math, Changsha 410073, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
regular fuzzy neural networks; universal approximation; cut-preserving fuzzy mapping;
D O I
10.1007/BF02917113
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The approximation capability of regular fuzzy neural networks to fuzzy functions is studied. When sigma is a nonconstant, bounded and continuous function on R, some equivalent conditions are obtained, with which continuous fuzzy functions can be approximated to any degree of accuracy by the four-layer feedforward regular fuzzy neural network [GRAPHICS] Finally a few examples of such fuzzy functions are given.
引用
收藏
页码:175 / 182
页数:8
相关论文
共 50 条