基于自适应学习速率的改进型BP算法研究  

Research of improved BP algorithm based on self-adaptive learning rate

作　　者：杨甲沛[1] 李锵[1] 刘郑[1] 袁晓琳[1] 

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《计算机工程与应用》2009年第11期56-58,66,共4页Computer Engineering and Applications

基　　金：国家自然科学基金No.60641011;天津市自然科学基金No.06YFJMJC15900~~

摘　　要：从感知器的结构及学习规则无法执行异或问题出发,用神经网络中的BP网络来解决异或问题,消除了感知器的局限性,但BP算法在具体实现中常会出现一些问题,如:收敛速度缓慢且与其他参数存在较强的耦合关系,局部极小等。对此,从前馈神经网络的原理出发,提出了一种自适应学习速率因子方法,用于对BP算法的改进,并将改进后的算法用于二维XOR问题及多维XOR问题的学习中。仿真实验证明,改进后的算法可显著提高网络的学习速度,且学习过程具有良好的收敛性及较强的鲁棒性。The XOR question can＇t be implemented by the structure and study regulation of feeling machines,started with which,this production uses BP network to solve the XOR question,which obliterates the limitation of the feeling machine.But problems come into existence in concrete apply of BP network,for example：The restrained rate is slow,and there is existence of the strong coupling relation with other parameters.Otherwise the partial is extreme minute.So according to the mechanism of feedforward neural network, it puts forward a method with self-adaptive learning rate factors for the improvement of BP algorithm.The improved algorithm is applied to the learning of two or more dimensions XOR question.The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.

关 键 词：神经网络 异或 自适应学习速率 反向传播 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]