自适应小波神经网络训练算法及其应用  

Adaptive Wavelet Neural Network Training Algorithm and Its Application

作　　者：江祥奎[1] 马超男[1] 

机构地区：[1]西安邮电大学自动化学院,西安710121

出　　处：《计算机与数字工程》2015年第9期1557-1560,共4页Computer & Digital Engineering

基　　金：陕西省教育厅自然科学类专项科研计划项目(编号:14JK1666;2013JK1073);西安邮电大学青年教师科研基金资助项目(编号:ZL2014-32)资助

摘　　要：小波神经网络是小波分析理论和人工神经网络两者结合的产物。为了解决BP算法易陷入极小值,收敛速度慢的问题。论文采用小波神经网络进行训练同时融合了带动量的BP算法,自适应调整小波的伸缩参数、平移参数和连接权值,并在其选定的范畴内尽可能多地提取信号特征。最后,论文以人口预测为例验证了自适应小波神经网络算法有效性。Wavelet neural network is the product combined with wavelet analysis theory and artificial neural network. In order to solve the problem of BP algorithm easily falling into the minimum, slow convergence. In this paper, wavelet neu- ral network is trained to drive while incorporating the amount of BP algorithm, adaptive wavelet stretching parameters, translation parameters and connection weights, and extract the signal features in their selected areas as much as possible. Fi- nally, an example to the population forecast is made to verify the effectiveness of adaptive wavelet neural network algorithm.

关 键 词：小波神经网络 训练算法 人口预测 自适应 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]