%0 Journal Article
%T Hidden Layer Performance Evaluation for Feedforward Neural Networks Based on Hidden Layer Growing Strategy<br>基于隐层生长策略的前馈神经网络隐层性能评测
%A PIAO Xiang-fan
%A CUI Rong-yi
%A HONG Bing-rong
%A <br>朴相范
%A 崔荣一
%A 洪炳熔
%J 计算机应用研究
%D 2005
%I 
%X A hidden layer performance evaluation method is discussed according to the model of least-squares approximation feedforward neural networks based on hidden layer growing strategy. Firstly, some spaces which affect the performance of feedforward neural networks are analyzed and four concepts of subspace, i.e. representation space, error space, target space and expend, are introduced. The error compensation performance of the hidden unit is analyzed. Finally, evaluation parameter of hidden layer performance is proposed, and the rationality and validity of proposed method are validated by reviewing classical BP algorithm and orthogonal algorithm.
%K Three-layered Feedforward Neural Networks
%K Hidden Layer Growing
%K Error Compensation Performance
%K Hidden Layer Evaluation Parameter<br>三层前馈神经网络
%K 隐层生长
%K 误差补偿性能
%K 隐层评测参数
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=431C6CB9EDBCF153&yid=2DD7160C83D0ACED&vid=BC12EA701C895178&iid=DF92D298D3FF1E6E&sid=94E7F66E6C42FA23&eid=F4B561950EE1D31A&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=7