首页 | 本学科首页   官方微博 | 高级检索  
     

模糊对向传播神经网络及其应用
引用本文:张志华,史罡,郑南宁,王天树.模糊对向传播神经网络及其应用[J].自动化学报,2000,26(1):56-60.
作者姓名:张志华  史罡  郑南宁  王天树
作者单位:1.西安交通大学人工智能与机器人研究所,西安
摘    要:通过把对向传播(CP)神经网络的竞争层神经元的输出函数定义为模糊隶属度函 数,提出了模糊对向传播(FCP)神经网络.该网络是CP网络的推广,它不仅能有效克服CP 存在的问题,而且具有全局函数逼近能力.在结构上,FCP网络同径向基函数(RBF)网络是等 价的.实际上,它是一种RBF网络,而且还是一种模糊基函数网络.FCP在时间序列预测中的 应用表明,FCP不仅在学习精度上,而且在泛化能力方面较之CP和RBF均有较大的改善.

关 键 词:对向传播网络    模糊隶属度函数    时间序列预测
收稿时间:1998-8-25
修稿时间:1998-08-25

FUZZY COUNTER PROPAGATION NEURAL NETWORK AND ITS APPLICATION
ZHANG Zhihua,SHI Gang,ZHENG Nanning,WANG Tianshu.FUZZY COUNTER PROPAGATION NEURAL NETWORK AND ITS APPLICATION[J].Acta Automatica Sinica,2000,26(1):56-60.
Authors:ZHANG Zhihua  SHI Gang  ZHENG Nanning  WANG Tianshu
Affiliation:1.Institute of AI and Robotics,Xi'an Jiaotong University,Xi'an
Abstract:A fuzzy counter propagation(FCP) neural network,which is a generalized model of the counter propagaton(CP) network,is proposed in this paper by defining output of the competitive unit of CP network as a fuzzy membership function. FCP not only is able to overcome the shortcomings of CP,but has the ability of universal function approximation as well.In view of network structure,FCP is equivalent to the radial basis function(RBF) network.In fact,FCP is an RBF network,also a fuzzy basis function network.In the end of this paper,the experiment to apply FCP to time series prediction shows that FCP outperforms CP and RBF in learning precision and generalizaton ability.
Keywords:Counter  propagation network  fuzzy membership function  time series prediction    
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》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