%0 Journal Article
%T System Analysis for Generalization of MFNN<br>前馈神经网络泛化性能力的系统分析
%A JIANG Xue-jun
%A TANG Huan-wen
%A <br>江学军
%A 唐焕文
%J 系统工程理论与实践
%D 2000
%I 
%X By the system analysis for the operation mechanism of multilayer feedforward neural networks(MFNN),this paper points out that the basic reasons affecting the generalization capability of MFNN are quality, quantity and representation ability of the training samples. And we give a method to raise the generalization capability of the complex system. The conclusion has been proved by experimental results.
%K MFNN
%K generalization capability
%K system analysis<br>多层前馈神经网络
%K 泛化能力
%K 系统分析
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=01BA20E8BA813E1908F3698710BBFEFEE816345F465FEBA5&cid=962324E222C1AC1D&jid=1D057D9E7CAD6BEE9FA97306E08E48D3&aid=DE94211AF6BF63E5&yid=9806D0D4EAA9BED3&vid=A04140E723CB732E&iid=5D311CA918CA9A03&sid=933658645952ED9F&eid=1371F55DA51B6E64&journal_id=1000-6788&journal_name=系统工程理论与实践&referenced_num=29&reference_num=0