[1]王少波,柴艳丽,梁醒培..神经网络学习样本点的选取方法比较[J].郑州大学学报(工学版),2003,24(01):63-65,69.[doi:10.3969/j.issn.1671-6833.2003.01.014]
　Wang Shaobo,Chai Yanli,Liang Xingpei.Comparison of the selection methods of neural network learning sample points[J].Journal of Zhengzhou University (Engineering Science),2003,24(01):63-65,69.[doi:10.3969/j.issn.1671-6833.2003.01.014]

点击复制

神经网络学习样本点的选取方法比较()

分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:

24

期数:

2003年01期

页码:

63-65,69

栏目:

出版日期:

1900-01-01

文章信息/Info

Title:

Comparison of the selection methods of neural network learning sample points

作者:

王少波; 柴艳丽; 梁醒培.

郑州机械研究所,河南,郑州,450052, 郑州机械研究所,河南,郑州,450052, 郑州机械研究所,河南,郑州,450052

Author(s):

Wang Shaobo; Chai Yanli; Liang Xingpei

关键词:

神经网络;  正交设计;  均匀设计

Keywords:

neural networks;  orthogonal design;  Uniform design

DOI:

10.3969/j.issn.1671-6833.2003.01.014

文献标志码:

A

摘要:

为了比较训练人工神经网络的所需样本点的选取,分别采用随机遍历法、正交设计法和均匀设计方法产生样本点,用于训练神经网络.分析结果表明,在样本点个数相同情况下,均匀设计法的代表性最好,正交设计法次之,而随机遍历法较差.随机遍历法随着样本点个数的增多,同样可以提高其代表性.当函数随变量在区间内变化较小(因素水平可以取的较少)时,正交设计法也不失为一个好的选择.均匀设计法在多变量,且每个变量需要选取较多水平数的情况下,更能体现它的优越性.

Abstract:

In order to compare the selection of sample points required for training artificial neural networks, the random traversal method, orthogonal design method and uniform design method are used to generate sample points for training neural networks. The analysis results show that under the same number of sample points, the uniform design method is the best representative, followed by the orthogonal design method, and the random traversal method is poor. The random traversal method can also improve its representativeness with the increase of the number of sample points. When the function varies less with the variable in the interval (less factor level can be taken), the orthogonal design method is also a good choice. The uniform design method can better reflect its superiority in the case of multiple variables and each variable needs to select a larger number of levels.

常用功能