线性分类器的PAC贝叶斯学习][PAC-Bayesian Learning of Linear Classifiers]

线性分类器的PAC贝叶斯学习 PAC-Bayesian Learning of Linear Classifiers


课程网址:	http://videolectures.net/icml09_marchand_pbll/
主讲教师:	Mario Marchand
开课单位:	拉瓦尔大学
开课时间:	2009-08-26
课程语种:	英语
中文简介:	我们提出了一个通用的PAC贝叶斯定理，从中可以简单地获得所有已知的PAC贝叶斯边界作为特定情况。我们还提出了不同的学习算法来寻找线性分类器，以最小化这些PAC贝叶斯风险边界。这些学习算法通常与AdaBoost和SVM竞争。
课程简介:	We present a general PAC-Bayes theorem from which all known PAC-Bayes bounds are simply obtained as particular cases. We also propose different learning algorithms for finding linear classifiers that minimize these PAC-Bayes risk bounds. These learning algorithms are generally competitive with both AdaBoost and the SVM.
关键词:	贝叶斯定理; 边界; 线性分类器
课程来源:	视频讲座网
最后编审:	2019-04-24：cwx
阅读次数:	99

境外开放课程导航