%0 Journal Article
%T DOBD Algorithm for Training Neural Network:Part II. Application<br>DOBD Algorithm for Training Neural Network: Part II. Application
%A WU Jian-yu
%A HE Xiao-rong
%A <br>WU Jian-yu吴建昱
%A HE Xiao-rong何小荣
%J 过程工程学报
%D 2002
%I 
%X In the first part of the article, a new algorithm for pruning networkDynamic Optimal Brain Damage(DOBD) is introduced. In this part, two cases and an industrial application are worked out to test the new algorithm. It is verified that the algorithm can obtain good generalization through deleting weight parameters with low sensitivities dynamically and get better result than the Marquardt algorithm or the cross-validation method. Although the initial construction of network may be different, the finial number of free weights pruned by the DOBD algorithm is similar and the number is just close to the optimal number of free weights. The algorithm is also helpful to design the optimal structure of network.
%K neural network
%K DOBD algorithm
%K Marquardt method
%K overfitting
%K pruning
%K training
%K application<br>neural
%K network
%K DOBD
%K algorithm
%K Marquardt
%K method
%K overfitting
%K pruning
%K training
%K application
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=3FCF8B1A330466D5&jid=B9EE12934D19905403D996AE65CEEEED&aid=F5A4D4394DBD38935D9A2556F67B367A&yid=C3ACC247184A22C1&vid=0B39A22176CE99FB&iid=38B194292C032A66&journal_id=1009-606X&journal_name=过程工程学报&referenced_num=0&reference_num=0