您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

J4 ›› 2012, Vol. 47 ›› Issue (3): 81-86.

• 数学 • 上一篇    下一篇

正则模糊神经网络对保极大值函数类的泛逼近性

段晨霞1,孙刚2,王贵君1*   

  1. 1.天津师范大学数学科学学院, 天津 300387; 2.大连海事大学轮机工程学院, 辽宁 大连 116026
  • 收稿日期:2011-04-08 出版日期:2012-03-20 发布日期:2012-04-01
  • 通讯作者: 王贵君(1962- ), 男, 教授, 主要研究方向为模糊神经网络与模糊积分. Email: tjwgj@126.com
  • 作者简介:段晨霞(1985- ),女,硕士研究生, 研究方向为模糊神经网络. Email: 2004060406@163.com
  • 基金资助:

    国家自然科学基金资助项目(60974144)

Universal approximation of three-layer regular fuzzy neural networks for a class of functions

DUAN Chen-xia1, SUN Gang2, WANG Gui-jun1*   

  1. 1. School of Mathematics Sciences, Tianjin Normal University, Tianjin 300387, China;
    2. Marine Engineering College, Dalian Maritime University, Dalian 116026, Liaoning, China
  • Received:2011-04-08 Online:2012-03-20 Published:2012-04-01

摘要:

在模糊神经网络中将紧集上多元连续函数类推广为保极大值函数类, 进而借助于保极大值性研究了紧集上扩展模糊函数类的特性和度量问题。最后,获得三层正则模糊神经网络关于其扩展模糊函数类具有泛逼近性, 并通过实例分析了目标输出与正则模糊神经网络实际输出的逼近效果。

关键词: 正则模糊神经网络;保极大值;支撑函数;泛逼近性

Abstract:

In fuzzy neural networks, the multi-variable continuous functions class is extended as a functions class of preserving maximum values on compact sets. The properties and the metric problems of the extended functions class on compact sets are studied by means of the concept of preserving maximum values. Finally, it is found that three-layer regular fuzzy neural networks possess approximation with respect to the extended fuzzy function class. Also, the approximation effect between the expected output and the real output of regular fuzzy neural networks is analysed and text is studied by an example.

Key words: regular fuzzy neural networks; preserving maximum value; support function; universal approximation

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!