%0 Journal Article
%T U-D Factorization-Based Nonlinear Programming Method and its Application in Neural Network Training<br>非线性规划U-D分解方法及其在神经网络训练中的应用
%A Shi Zhongke
%A <br>史忠科
%J 自动化学报
%D 1995
%I 
%X To solve convergence rate problems of often used DFP and BFCS methods, the stable construction of inverse Hassian matrix are presented. To get high numerical stability and computational efficiency, U-D factorization-based DFP and BFGS algorithms are developed. In the new methods the positive definiteness of the inverse matrix H is ensured and both the stability and convergence of the algorithm is improved. By using rank-one U-D factorization updates of H, the numerical accuracy and efficiency are increased. Operational counts for computing H show that the efficiency of the new algorithm is increased by 20% and the storages of matrix H is reduced by 50%. Results of several numerical example show that the optimization problems can be solved by using the programming methods presented in this paper and accurate results may be obtained.
%K Nonlinear programming
%K large scale problem
%K neural network
%K learing algorith
%K unconstrained optimization<br>非线性规划
%K 神经网络
%K 学习算法
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=27C73708C5D90D03483356FC9F0FE9FC&yid=BBCD5003575B2B5F&vid=659D3B06EBF534A7&iid=B31275AF3241DB2D&sid=7F9B7E84827A650F&eid=0B52E912EAFE3700&journal_id=0254-4156&journal_name=自动化学报&referenced_num=2&reference_num=1