随机投影,边距,内核和特征选择Random projection, margins, kernels, and feature-selection |
|
课程网址: | http://videolectures.net/slsfs05_blum_rpmkf/ |
主讲教师: | Avrim Blum |
开课单位: | 卡内基梅隆大学 |
开课时间: | 2007-02-25 |
课程语种: | 英语 |
中文简介: | 随机投影是一种简单的技术,通常可以洞察诸如“为什么拥有较大利润率这是一件好事?”之类的问题。或“内核实际上在做什么,它们与功能选择有何相似之处?”在本演讲中,我将描述一些使用随机投影的简单学习算法。然后,我将讨论在给定内核作为黑盒函数的情况下,如何使用各种形式的随机投影来提取显式的小特征空间,以捕获给定内核函数的大部分功能。 |
课程简介: | Random projection is a simple technique that can often provide insight into questions such as "why is it good to have a large margin?" or "what are kernels really doing and how are they similar to feature selection?" In this talk I will describe some simple learning algorithms using random projection. I will then discuss how, given a kernel as a black-box function, we can use various forms of random projection to extract an explicit small feature space that captures much of the power of the given kernel function. |
关 键 词: | 随机投影; 简单学习算法; 内核函数 |
课程来源: | 视频讲座网 |
最后编审: | 2019-09-21:cwx |
阅读次数: | 37 |