%0 Journal Article
%T AN ADAPTIVE TIME DELAY WAVELET NEURAL NETWORK FOR SIGNAL APPROXIMATION<br>用于信号逼近的自适应时延小波神经网络
%A He Zhenya
%A Li Wenhua
%A Wei Chengjian
%A <br>何振亚
%A 李文化
%A 蔚承建
%J 电子与信息学报
%D 1998
%I 
%X Wavelet neural networks (WNN) is a powerful tool for function approximation. In this paper a new model named adaptive time delay WNN(ATDWNN) is proposed which combines tune delay neural network and wavelet decomposition. ATDWNN is used to approximate signals having different time delays hi the same class. In order to train ATDWNN, time mechanism based competition learning is also proposed. It is shown through experiments that ATDWNN can not only approximate signals having different time delays by th'e same superwavelet, but also detect these time delays successfully.
%K Adaptive time delay wavelet neural network
%K Signal approximation
%K Time competition<br>自适应时延小波神经网络
%K 信号逼近
%K 时间竞争
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=05A31A6878E7953ACD69BA61FA77DDFF&yid=8CAA3A429E3EA654&vid=A04140E723CB732E&iid=94C357A881DFC066&sid=1A0C7C60D40EFD74&eid=44E78A5D1B37D836&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=8