| 一种交互学习的属性划分算法 |
| |
| 引用本文： | 宋华珠,钟珞,赵广辉,夏红霞. 一种交互学习的属性划分算法[J]. 武汉理工大学学报(信息与管理工程版), 2005, 27(2): 187-191 |
| |
| 作者姓名： | 宋华珠 钟珞 赵广辉 夏红霞 |
| |
| 作者单位： | 武汉理工大学,计算机科学与技术学院,湖北,武汉,430070 |
| |
| 摘 要： | 首先给出了属性分割的有效性测试算法,它能检测基于当前分割的交互学习算法是否优越于传统的不划分属性的单一数据集的学习算法;进一步,给出了渐进式自动属性集合的划分算法。基于大规模卫星环境监测数据的实验表明,上述两种算法能对有效地分割数据集合,使学习能力得到明显提高。
|
| 关 键 词： | 标记数据 交互学习 视图有效性检测 自动视图测试 |
| 文章编号： | 1007-144X(2005)02-0187-04 |
| 修稿时间： | 2004-10-27 |
An Attribute Division Algorithm for Co -training |
| |
| Song Huazhu,Zhong Luo,Zhao Guanghui,Xia Hongxia. An Attribute Division Algorithm for Co -training[J]. Journal of Wuhan University of Technology(Information & Management Engineering), 2005, 27(2): 187-191 |
| |
| Authors: | Song Huazhu Zhong Luo Zhao Guanghui Xia Hongxia |
| |
| Affiliation: | Song Huazhu,Zhong Luo,Zhao Guanghui,Xia HongxiaSong Huazhu:Lect., School of Computer Science and Technology,WUT,Wuhan 430063,China. |
| |
| Abstract: | A feature split algorithm is presented which can test whether this algorithm will outperform the traditional algorithms without using a feature split with a just single view. A progressive approach is given for detecting a good feature split for co-training. Experimental results indicate that the progressive method always outperforms the traditional methods in supplying the feature division. |
| |
| Keywords: | labeled data co-training algorithm view validation automatic view detection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
