摘要
通过分析多元模糊值 Bernstein多项式的近似特性 ,证明了 4层前向正则模糊神经网络 (FNN)的逼近性能。该类网络构成了模糊值函数的一类泛逼近器 ,即在欧氏空间的任何紧集上 ,任意连续模糊值函数能被这类 FNN逼近到任意精度。最后通过实例给出了实现这种近似的具体步骤。
The systematic analysis on approximation capability of four-layer feedforward regular fuzzy neural network (FNN) is presented. This is done by fuzzy valued multivariate Bernstein polynomial whose approximation to fuzzy valued functions is guaranteed. Such a four-layer FNN constitutes a universal approximator of fuzzy valued function. That is, each continuous fuzzy valued function defined on any compact set of Euclidean space can be approximated by the FNN to any degree of accuracy. A numerical example shows the realization process of the approximation.
出处
《控制与决策》
EI
CSCD
北大核心
2003年第1期19-23,28,共6页
Control and Decision
基金
国家自然科学基金资助项目 (6 99740 41
6 99740 0 6 )
