%0 Journal Article
%T Learning Capability of Feedforward Networks<br>前馈神经网络的学习能力
%A TIAN Da-gang
%A <br>田大钢
%J 系统工程理论与实践
%D 2004
%I 
%X A new grouping subnetwork use to improve Huang's significant result on the learning capability of two-hidden-layer feedforward networks (TLFNs) is presented. The result that feedforward netwroks with 2(2N)~((1/2)) 2 hidden neurons can learn any \$N\$ distinct samples with any arbitrarily small error be obtained. New method ensures the result is valid not only for the sigmoid function, but for a wide class of activation functions.
%K neural networks
%K learning capability
%K classification<br>神经网络
%K 学习能力
%K 分类
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=01BA20E8BA813E1908F3698710BBFEFEE816345F465FEBA5&cid=962324E222C1AC1D&jid=1D057D9E7CAD6BEE9FA97306E08E48D3&aid=1380AD08D4770667&yid=D0E58B75BFD8E51C&vid=B91E8C6D6FE990DB&iid=708DD6B15D2464E8&sid=228A710F49B6CE58&eid=35FC3610259C2B32&journal_id=1000-6788&journal_name=系统工程理论与实践&referenced_num=2&reference_num=5