概率密度估计框架A Framework for Probability Density Estimation |
|
课程网址: | http://videolectures.net/ripd07_david_fbd/ |
主讲教师: | Shai Ben-David |
开课单位: | 滑铁卢大学 |
开课时间: | 2008-02-25 |
课程语种: | 英语 |
中文简介: | 该演讲通过评估一组“测试函数”的性能,介绍了学习概率密度函数的新框架。理论分析表明,我们可以通过训练它来适应一个小的子样本来定制一类任务的分布。在用于分发的分布类的复杂性和任务集的复杂性之间存在折衷。实验证据支持理论分析。 |
课程简介: | The talk introduces a new framework for learning probability density functions by assessing their performance against a set of 'test functions'. A theoretical analysis suggests that we can tailor a distribution for a class of tasks by training it to fit a small subsample. There is a trade-off between the complexity of the class of distributions used for the distribution and the complexity of the set of tasks. Experimental evidence is given to support the theoretical analysis. |
关 键 词: | 测试函数; 概率密度; 任务集 |
课程来源: | 视频讲座网 |
最后编审: | 2019-09-17:lxf |
阅读次数: | 63 |