BP算法的改进及其在库存数量预测中的应用  

BP Algorithm and Its Application on Store Amount Prediction

作　　者：王红霞[1] 僧德文[1] 

机构地区：[1]浙江水利水电专科学校,浙江杭州310018

出　　处：《浙江水利水电专科学校学报》2006年第4期34-37,共4页Journal of Zhejiang Water Conservancy and Hydropower College

基　　金：浙江省教育厅基金资助项目(20060001;21205);浙江省水利厅基金资助项目(RC0605);浙江省高校青年教师基金资助项目(21223)

摘　　要：针对BP算法收敛速度较慢、局部极值等缺点,提出了一种改进的BP算法.根据训练误差改变转移函数的惩罚因子并且对学习步长作自动调节.实践结果表明,改进后的BP算法可大大提高算法的函数拟合度和收敛度,减少与实际值间的误差.BP Algorithm has some disadvantages, such as local minima, weights sensitivity of initial value, total dependence on gradient information, etc. An improved algorithm is proposed, which can wain a neural network by changing the gradient of Sigmoid function according to the errors in training and adjusting neural network＇s learning rate automatically. The simulation results indicate that the algorithm proposed can improve the curve fitting and convergence, and reduce the discrepancy between the fact data and the measure data.

关 键 词：前馈神经网络 BP算法 学习步长 惩罚因子 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]