前馈网络的一种超线性收敛BP学习算法  

Super-Linearly Convergent BP Learning Algorithm for Feedforward Neural Networks

作　　者：梁久祯[1] 何新贵[1] 黄德双[2] 

机构地区：[1]北京航空航天大学计算机科学与工程系,北京100083 [2]北京系统工程研究所,北京100101

出　　处：《软件学报》2000年第8期1094-1096,共3页Journal of Software

基　　金：国家自然科学基金! (No.6 970 5 0 0 1)资助

摘　　要：分析传统 BP算法存在的缺点 ,并针对这些缺点提出一种改进的 BP学习算法 .证明该算法在一定条件下是超线性收敛的 ,并且该算法能够克服传统 BP算法的某些弊端 ,算法的计算复杂度与简单 BP算法是同阶的 .实验结果说明这种改进的 BP算法是高效的、可行的 .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 shown 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 algorithm. Finally, two computing examples are given. Simulation results illustrate that this algorithm is highly effective and practicable.

关 键 词：前馈神经网络 超线性收敛 BP网络 学习算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]