| 基于非对称度量的分类器优化问题 |
| |
| 引用本文： | 陈少艾,陈少白,李文.基于非对称度量的分类器优化问题[J].武汉科技大学学报(自然科学版),2007,30(4):426-429. |
| |
| 作者姓名： | 陈少艾 陈少白 李文 |
| |
| 作者单位： | 1. 武汉船舶职业技术学院机械工程系,湖北,武汉,430050
2. 武汉科技大学理学院,湖北,武汉,430081 |
| |
| 摘 要： | 研究在模式识别中可测分类器之间的非对称度量及优化问题。以分类器之间相对平均分类错误率建立分类器之间的非对称度量，进一步研究了子空间上的最优分类器及其估计。最后对模式识别中两个重要的例子在非对称度量空间上进行了讨论。
|
| 关 键 词： | 非对称度量空间 模式识别 可测分类器 |
| 文章编号： | 1672-3090（2007）04-0426-04 |
| 修稿时间： | 2007-01-10 |
Quasi-pseudo-metrics of measurable classifiers |
| |
| Chen Shaoai,Chen Shaobai,Li Wen.Quasi-pseudo-metrics of measurable classifiers[J].Journal of Wuhan University of Science and Technology(Natural Science Edition),2007,30(4):426-429. |
| |
| Authors: | Chen Shaoai Chen Shaobai Li Wen |
| |
| Institution: | 1. Department of Mechanical Engineering, Wuhan Institute of Shipbuilding Technology, Wuhan 430050, China; 2. College of Science, Wuhan University of Science and Technology, Wuhan 430081, China |
| |
| Abstract: | This paper studies the quasi-pseudo-metrics of measurable classifiers in pattern recognition. A quasi-pseudo-metrics of measurable classifiers in probability spaces is proposed, which is an average expense between classifiers. The optimal classifiers in subspace and their estimations are investigated, and two important examples are discussed in the space. |
| |
| Keywords: | quasi-metric space pattern recognition measurable classifier |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
