The Study of Learning Algorithm the BP Neural Network Based on Extended BFGS Method
In this paper, a new BP learning algorithm based on extended BFGS method is presented in order to get the solutions for some learning problems of traditional BP Neural Network, such as the slow rate of convergence and poor stabilization. Introduce the modified Newton descent method to the BFGS method which is used to obtain good variables. The single variable search, which the ordinary BFGS arithmetic often has to do, is not required in the extended BFGS method; but the optimized results can be reached step by step. Numerical test is carried out by the extended BFGS method and the others learning method of BP Neural Network, and comparisons of the results demonstrate that the new algorithm is better than the others in numerical stability and convergence.
extended-BFGS method Newton descent method BP Neural Network learning algorithm
Ren Yu-yan Xu Yi-xin Bao Jie
Department of Automation University of Yanshan Qinhuangdao, Hebei Province, China Department of Automation NDRC,P. R. China Beijing,China
国际会议
长春
英文
208-211
2010-08-24（万方平台首次上网日期，不代表论文的发表时间）