首页 | 本学科首页   官方微博 | 高级检索  
     

APPROXIMATION MULTIDIMENSION FUCTION WITH FUNCTIONAL NETWORK
作者姓名:Li  Weibin  Liu  Fang  Jiao  Licheng  Zhang  Shuling  Li  Zongling
作者单位:[1]Institute of Graphics and Image Processing, Xianyang Normal University, Xianyang 712000, China [2]National Key Laboratory for Radar Signal Processing, Xidian University, Xi'an 710071, China [3]Insititute of Intelligent Information Processing, Xidian University, Xi'an 710071, China
基金项目:Partly supported by the National Natura Science Foundation of China(No.60133010), the Natura Science Foundation of Education Department of Shaanxi Province (No.05JK312), and the Natura Science Foundation of Xianyang Normal University(No.04XSYK101 )
摘    要:The functional network was introduced by E.Catillo, which extended the neural network. Not only can it solve the problems solved, but also it can formulate the ones that cannot be solved by traditional network. This paper applies functional network to approximate the multidimension function under the ridgelet theory. The method performs more stable and faster than the traditional neural network. The numerical examples demonstrate the performance.

关 键 词:泛函网络  神经网络  神经元  逼近值  时频系统
收稿时间:2003-02-25
修稿时间:2004-03-08

Approximation multidimension fuction with functional network
Li Weibin Liu Fang Jiao Licheng Zhang Shuling Li Zongling.APPROXIMATION MULTIDIMENSION FUCTION WITH FUNCTIONAL NETWORK[J].Journal of Electronics,2006,23(1):81-84.
Authors:Weibin Li PhD  Fang Liu  Licheng Jiao  Shuling Zhang  Zongling Li
Affiliation:1. Institute of Graphics and Image Processing,Xianyang Normal University,Xianyang 712000,China;National Key Laboratory for Radar Signal Processing,Xidian University,Xi' an 710071,China;Insititute of Intelligent Information Processing,Xidian University,Xi' an 710071,China
2. National Key Laboratory for Radar Signal Processing,Xidian University,Xi' an 710071,China;Insititute of Intelligent Information Processing,Xidian University,Xi' an 710071,China
3. Institute of Graphics and Image Processing,Xianyang Normal University,Xianyang 712000,China
Abstract:The functional network was introduced by E.Catillo, which extended the neural network. Not only can it solve the problems solved, but also it can formulate the ones that cannot be solved by traditional network This paper applies functional network to approximate the multidimension function under the ridgelet theory. The method performs more stable and faster than the traditional neural network. The numerical examples demonstrate the performance.
Keywords:Functional network  Ridgelet  Approximation
本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录!
点击此处可从《电子科学学刊(英文版)》浏览原始摘要信息
点击此处可从《电子科学学刊(英文版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号