BP神经网络结点数选取的改进方法及其应用  

Improved method and application to choose the nodes for BP neural network

作　　者：张庆庆[1] 贺兴时[1] 

机构地区：[1]西安工程大学理学院,陕西西安710048

出　　处：《西安工程大学学报》2008年第4期502-505,共4页Journal of Xi’an Polytechnic University

基　　金：陕西省教育厅自然科学专项基金资助项目(06JK286)

摘　　要：提出一种改进的隐含层神经元个数的选取方法.该方法基于隐含层神经元输出之间的相关关系,估计隐含层结点数,把隐含层结点的改进算法用于物种选取的实例中,通过MATLAB编程实现,并与回归分析做出的结果进行比较.结果表明,该方法对建立BP神经网络结构有一定的借鉴作用.An improved method for choosing the number of nodes in hidden layer was proposed. The method is based on the linear correlation of the output of hidden layers to estimate the number. The last part put the improved method into the application of species select, using MATLAB program to realize and making comparison with the result of regression analysis. The results show that the method makes advance in guiding to the structure of the BP neural network.

关 键 词：BP神经网络 隐含层结点 线性相关 物种选取 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]