%0 Journal Article
%T NEW IMPROVEMENT OF UNCERTAINTY RELATION SUITED TO OVERFITTING OF BP NEURAL NETWORK<br>BP网络过拟合现象满足的不确定关系新的改进式
%A LI Zuo Yong
%A PENG Li Hong
%A <br>李祚泳
%A 彭荔红
%J 红外与毫米波学报
%D 2002
%I Science Press
%X Based on the analogue of general uncertainty relation in information transmitting processes, by the introduction of multi correlative coefficient R to manifest the complexity of the function and the hidden unit h to manifest the complexity of the network structure, a general uncertainty relation between the learning ability and the generalization ability suited to overfitting of BP neural network was revealed in the modeling of BP neural network. Tests of numerical simulation for 12 kinds of complicated function were carried out to determine the value distribution (1×10 -5 ～5×10 -4 ) of overfitting parameter in the uncertainty relation. Based on the uncertainty relation, the judgement of overfitting in the training process of gived sample sets using BP network was given.
%K BP network
%K overfitting
%K learning ability
%K generalization ability
%K uncertainty relation<br>BP网络
%K 过拟合
%K 学习能力
%K 推广能力
%K 不确定关系
%K 人工神经网络
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=D3B4F771D1A06062008B4D0A2EF05996&aid=300BE491B2E544AB&yid=C3ACC247184A22C1&vid=659D3B06EBF534A7&iid=E158A972A605785F&sid=2AC7DCCBBC26ECF8&eid=D0182A31A5EB14BA&journal_id=1001-9014&journal_name=红外与毫米波学报&referenced_num=1&reference_num=8