前向网络作为模糊函数泛逼近器的一致性分析  

Uniform Approximation for Fuzzy Functions of Feedforword Neural Networks

作　　者：赵芬霞[1] 张与鸿[1] 

机构地区：[1]天津商业大学理学院,天津300134

出　　处：《模糊系统与数学》2012年第5期132-137,共6页Fuzzy Systems and Mathematics

基　　金：天津市高等学校科技发展基金资助项目(20110519)

摘　　要：前向神经网络的泛逼近性一直是神经网络的研究热点。本文给出了连续模糊函数的定义,依Hausdorff度量,借助模糊值Bernstein多项式关于连续模糊函数的逼近性质,证明了前向网络作为模糊函数泛逼近器的一致逼近性结果,并通过实例给出了逼近性的具体实现过程。Uniform approximation of feedforward neural networks has always been a hot spot on neural networks＇ research. In this paper, the definition of continuous fuzzy functions is given, according to Hausdorff measure, through the approximation of fuzzy-valued Bernstein polynomials on continuous fuzzy functions, the consistent approximation of feedforward neural network as a universal approximator of fuzzy functions is proved, and an example is shown to explain the realization process of the approximation.

关 键 词：连续模糊函数 BERNSTEIN多项式 泛逼近器 

分 类 号：O159[理学—数学]