基于小波网络的BP算法改进研究

Research on improvement of BP algorithm based on WNN

对BP算法的特点进行了分析,在权值平衡算法的基础上,应用小波网络对其进行改造,提出了基于小波网络的BP权值平衡算法,给出了具体的算法步骤,仿真结果证明该算法既具有BP网络的简捷性,又能够提高学习速度和精度,避免了BP网络易出现的收敛速度慢、易产生局部最优解的问题,是一种较好的神经网络学习算法。

The characters of BP algorithm are analyzed in this paper.On the basis of the weight balance algorithm,BP algorithm is modified by WNN.And the BP weight balance algorithm based on WNN is proposed and the concrete steps of this algorithm are presented.Thls improved weight balance algorithm adopts one kind of continuous wavelet functions--Gauss wavelet function to replace sigmoid Function to be implicit layer challenging function,and also bring in form factor vk to balance the value of weighting regulation in BP.Theoretical analysis and simulation result show it is an effective algorithm,which not only is simple and efficient like BP algorithm but also can increase the learning speed and precision,avoid the problem that BP neural network is easy to be trapped in local minima and its convergence speed is slow.