| BP神经网络合理隐结点数确定的改进方法 |
| |
| 引用本文： | 邹方林,冷晟,廉鹏飞,晁翠华.BP神经网络合理隐结点数确定的改进方法[J].系统仿真技术,2014(2):154-158. |
| |
| 作者姓名： | 邹方林 冷晟 廉鹏飞 晁翠华 |
| |
| 作者单位： | 南京航空航天大学机电学院,江苏南京210016 |
| |
| 基金项目： | 航空制造过程中工程变更传播机制与自修复响应方法研究资助项目（51205201） |
| |
| 摘 要： | 合理选择隐含层结点个数是BP神经网络构造中的关键问题,对网络的适应能力、学习速率都有重要的影响.在此提出一种确定隐结点个数的改进方法.该方法基于隐含层神经元输出之间的线性相关关系与线性无关关系,对神经网络隐结点个数进行削减,缩减网络规模.以零件工艺过程中的加工参数作为BP神经网络的输入,加工完成的零件尺寸作为BP神经网络的输出建立模型,把该方法应用于此神经网络模型中,其训练结果证明了该方法的有效性.
|
| 关 键 词： | BP神经网络 隐结点个数 线性相关 线性无关 |
An Improved Method on Determining the Reasonable Number of Hidden Nodes of BP Neural Network |
| |
| ZOU Fanglin,LENG Sheng,LIAN Pengfei,CHAO Cuihua.An Improved Method on Determining the Reasonable Number of Hidden Nodes of BP Neural Network[J].System Simulation Technology,2014(2):154-158. |
| |
| Authors: | ZOU Fanglin LENG Sheng LIAN Pengfei CHAO Cuihua |
| |
| Affiliation: | (College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics ＆ Astronautics, Nanjing 210016, China) |
| |
| Abstract: | The number of hidden units in a BP neural network is significant in characterizing the performance of the network. It greatly influences generalization ability and learning speed. This paper proposes an improved method of determining the number of hidden nodes. The method, based on the linear correlation and linear independent relationship of the output of hidden layers, reduces the number of hidden units and the size of network. Taking the machining process parameters as the input of BP neural network and taking the completed part as the output, this paper applied the method to neural network model. The training results demonstrate the effectiveness of this method |
| |
| Keywords: | BP neural network the number of hidden nodes linear correlation linear independent |
| 本文献已被 维普 等数据库收录！ |
|
