首页 → 工程与技术科学
使用未标记数据的最佳组合分类器Optimally Combining Classifiers Using Unlabeled Data |
|
| 课程网址: | https://videolectures.net/videos/colt2015_balsubramani_unlabeled_... |
| 主讲教师: | Akshay Balsubramani |
| 开课单位: | 信息不详。欢迎您在右侧留言补充。 |
| 开课时间: | 2025-02-04 |
| 课程语种: | 英语 |
| 中文简介: | 我们提出了一种用于二元分类的分类器集成集合的最坏情况分析。预测最小化错误的任务是在给定的未标记数据集(转换设置)上进行游戏,其中先前的标签信息被编码为游戏的约束条件。这个博弈的极大极小解确定了分类器的加权组合比任何单个分类器表现更好的情况。 |
| 课程简介: | We develop a worst-case analysis of aggregation of classifier ensembles for binary classification. The task of predicting to minimize error is formulated as a game played over a given set of unlabeled data (a transductive setting), where prior label information is encoded as constraints on the game. The minimax solution of this game identifies cases where a weighted combination of the classifiers can perform significantly better than any single classifier. |
| 关 键 词: | 转化设置; 二元分类; 分类器 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2025-03-27:zsp |
| 最后编审: | 2025-03-27:zsp |
| 阅读次数: | 58 |
