%0 Journal Article
%T CONSTRUCTIONAL METHOD OF FUNCTION APPROXIMATION OF GNN<br>G神经网络函数映射能力的构造性证明
%A Wei Gang
%A Tian Chuanjun
%A <br>韦岗
%A 田传俊
%J 电子与信息学报
%D 2001
%I 
%X In this paper, the function approximation of Gelenbe Neural Network (GNN) is discussed and it is proved that GNN can approximate any G-type polynomial by using constructional method. Number of units used by this method can be reduced to 2/(n + 1) of that used by previous methods for a same G-type polynomial, where n is the degree of G-type polynomial.
%K Neural network
%K GNN
%K Function approximation
%K G-type polynomial<br>G神经网络
%K 函数映射
%K 构造性证明
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=9B942759087523FC&yid=14E7EF987E4155E6&vid=EA389574707BDED3&iid=708DD6B15D2464E8&sid=9F83C44826B8A7D6&eid=BAEC9CADFE1F0CCC&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=10