在线学习与布雷格曼分歧][Online Learning and Bregman Divergences]

在线学习与布雷格曼分歧 Online Learning and Bregman Divergences


课程网址:	http://videolectures.net/mlss06tw_warmuth_olbd/
主讲教师:	Manfred K. Warmuth
开课单位:	加州大学圣克鲁兹分校
开课时间:	2007-02-25
课程语种:	英语
中文简介:	L 1：在线学习简介（预测与最佳专家一样好，预测与专家的最佳线性组合，添加剂与乘法更新系列一样好）\\ L 2：Bregman分歧和损失界限（Bregman分歧介绍，线性情形的相对损失界限，非线性情形和匹配损失，对偶性和与指数族的关系）\\ L 3：扩展，解释，应用（在线到批量转换，关于权重向量的先验信息，一些应用）
课程简介:	L 1: Introduction to Online Learning (Predicting as good as the best expert, Predicting as good as the best linear combination of experts, Additive versus multiplicative family of updates)\\ L 2: Bregman divergences and Loss bounds (Introduction to Bregman divergences, Relative loss bounds for the linear case, Nonlinear case & matching losses, Duality and relation to exponential families)\\ L 3: Extensions, interpretations, applications (Online to Batch Conversions, Prior information on the weight vector, Some applications)
关键词:	在线学习; 线性组合; 损失界限
课程来源:	视频讲座网
最后编审:	2019-07-24：cwx
阅读次数:	65

境外开放课程导航