首页 | 官方网站   微博 | 高级检索  
     

人工神经网络中隐含层节点与训练次数的优化
引用本文:高大文,王鹏,蔡臻超.人工神经网络中隐含层节点与训练次数的优化[J].哈尔滨工业大学学报,2003,35(2):207-209.
作者姓名:高大文  王鹏  蔡臻超
作者单位:哈尔滨工业大学,市政环境工程学院,黑龙江,哈尔滨,150090
基金项目:哈尔滨工业大学跨学科交叉性研究基金资助项目(HITMD2 0 0 0 .2 8) .
摘    要:目前构建定量构效关系人工神经网络模型中隐含层节点数和网络训练次数大多是依靠试验方法来确定,针对该方法运算工作量较大、模型质量和预测精度没有保证等问题,通过编写程序获得有关网络的预测精度和百分误差与网络隐含层节点数和训练次数之间关系的大量数据,采用Matlab语言分别绘制预测精度和百分误差与网络隐含层节点数和训练次数之间的三维关系图,从图中可以很容易判断出达到最佳预测精度和最小百分误差的隐含层节点数和训练次数。该方法和技术从根本上提高了选择人工神经网络隐含层节点数和训练次数方法的效率。

关 键 词:隐含层节点  训练次数  优化  人工神经网络
文章编号:0367-6234(2003)02-0207-03
修稿时间:2002年5月21日

Optimization of hidden nodes and training times in artificial neural network
GAO Da wen,WANG Peng,CAI Zhen chao.Optimization of hidden nodes and training times in artificial neural network[J].Journal of Harbin Institute of Technology,2003,35(2):207-209.
Authors:GAO Da wen  WANG Peng  CAI Zhen chao
Abstract:In order to find out the number of hidden nodes and the training times of network in QSAR, a large number of data has been gathered for the relationships between the predictability and percentage error of network and the number of hidden nodes and the training times by running programs, and a three-dimension plot has been drawn by applying Matlab. The number of hidden nodes and the training times can be easily found with the least percentage error and the best predict precision and the efficiency in selecting the number of hidden nodes and the training times can therefore easily improved.
Keywords:node in hidden layer  training time  optimization  artificial neural network
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号