%0 Journal Article
%T DOBD Algorithm for Training Neural Network: Part I. Method
%A WU Jian-yu
%A HE Xiao-rong
%A
吴建昱
%A 何小荣
%J 过程工程学报
%D 2002
%I
%X Overfitting is one of the important problems that restrain the application of neural network. The traditional OBD (Optimal Brain Damage) algorithm can avoid overfitting effectively. But it needs to train the network repeatedly with low calculational efficiency. In this paper, the Marquardt algorithm is incorporated into the OBD algorithm and a new method for pruning network-the Dynamic Optimal Brain Damage (DOBD) is introduced. This algorithm simplifies a network and obtains good generalization through dynamically deleting weight parameters with low sensitivity that is defined as the change of error function value with respect to the change of weights. Also a simplified method is presented through which sensitivities can be calculated during training with a little computation. A rule to determine the lower limit of sensitivity for deleting the unnecessary weights and other control methods during pruning and training are introduced. The training course is analyzed theoretically and the reason why DOBD algorithm can obtain a much faster training speed than the OBD algorithm and avoid overfitting effectively is given.
%K neural network
%K DOBD algorithm
%K Marquardt
%K overfitting
%K pruning
%K training
%K method
DOBD算法
%K 人工神经网络
%K 研究方法
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=3FCF8B1A330466D5&jid=B9EE12934D19905403D996AE65CEEEED&aid=634C7A784D3DCC27&yid=C3ACC247184A22C1&vid=0B39A22176CE99FB&iid=0B39A22176CE99FB&sid=73579BC9CFB2D787&eid=5BC9492E1D772407&journal_id=1009-606X&journal_name=过程工程学报&referenced_num=0&reference_num=11