%0 Journal Article
%T Super-Linearly Convergent BP Learning Algorithm for Feedforward Neural Networks<br>前馈网络的一种超线性收敛BP学习算法
%A LIANG Jiu-zhen
%A HE Xin-gui
%A HUANG De-shuang
%A <br>梁久祯
%A 何新贵
%A 黄德双
%J 软件学报
%D 2000
%I 
%X In this paper, some shortages of traditional BP learning algorithm are analyzed. To avoid these shortages, a modified BP learning algorithm is proposed. It is s hown that this algorithm is super-linearly convergent under certain conditions. This algorithm can overcome some shortages of traditional BP learning algorithm , and has the same order of computation complexity as the traditional BP algorit hm. Finally, two computing examples are given. Simulation results illustrate tha t this algorithm is highly effective and practicable.
%K Feedforward neural network
%K BP learning algorithm
%K convergence
%K super-linear c onvergence<br>前馈神经网络
%K BP学习算法
%K 收敛性
%K 超线性收敛.
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=7735F413D429542E610B3D6AC0D5EC59&aid=1A48291C6C19F51B&yid=9806D0D4EAA9BED3&vid=708DD6B15D2464E8&iid=5D311CA918CA9A03&sid=6B48C3DA6EA0194C&eid=BE1F29C193C78397&journal_id=1000-9825&journal_name=软件学报&referenced_num=17&reference_num=3