图 书 馆
通过不断演变的流数据进行主动学习Active learning with evolving streaming data |
|
| 课程网址: | http://videolectures.net/ecmlpkdd2011_zliobaite_data/ |
| 主讲教师: | Indrė Žliobaitė |
| 开课单位: | 伯恩茅斯大学 |
| 开课时间: | 2011-11-29 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Since labeling data is often both laborious and costly, the labeled data available in many applications is rather limited. Active learning is a learning approach which actively selects unlabeled data points to label as a way to alleviate the labeled data deficiency problem. In this paper, we extend a previous active learning method called transductive experimental design (TED) by proposing a new unlabeled data selection criterion. Our method, called discriminative experimental design (DED), incorporates both margin-based discriminative information and data distribution information and hence it can be seen as a discriminative extension of TED. We report experiments conducted on some benchmark data sets to demonstrate the effectiveness of DED. |
| 关 键 词: | 标记数据; 主动学习; 数据选择准则; 判别信息 |
| 课程来源: | 视频讲座网公开课 |
| 最后编审: | 2019-05-26：cwx |
| 阅读次数: | 53 |