18.465 Topics in Statistics: Statistical Learning Theory, Spring 2004

Panchenko, Dmitry A.

Author(s)

Panchenko, Dmitry A.

Download18-465Spring-2004/OcwWeb/Mathematics/18-465Spring-2004/CourseHome/index.htm (12.20Kb)

Alternative title

Topics in Statistics: Statistical Learning Theory

Terms of use

Usage Restrictions: This site (c) Massachusetts Institute of Technology 2003. Content within individual courses is (c) by the individual authors unless otherwise noted. The Massachusetts Institute of Technology is providing this Work (as defined below) under the terms of this Creative Commons public license ("CCPL" or "license"). The Work is protected by copyright and/or other applicable law. Any use of the work other than as authorized under this license is prohibited. By exercising any of the rights to the Work provided here, You (as defined below) accept and agree to be bound by the terms of this license. The Licensor, the Massachusetts Institute of Technology, grants You the rights contained here in consideration of Your acceptance of such terms and conditions.

Metadata

Show full item record

Abstract

The main goal of this course is to study the generalization ability of a number of popular machine learning algorithms such as boosting, support vector machines and neural networks. Topics include Vapnik-Chervonenkis theory, concentration inequalities in product spaces, and other elements of empirical process theory.

Date issued

2004-06

URI

http://hdl.handle.net/1721.1/39660

Department

Massachusetts Institute of Technology. Department of Mathematics

Other identifiers

18.465-Spring2004

local: 18.465

local: IMSCP-MD5-6ad0fb431d0c042966021b0187148673

Keywords

machine learning algorithms, boosting, support vector machines, neural networks, Vapnik- Chervonenkis theory, concentration inequalities in product spaces, empirical process theory

Collections

MIT OCW Archived Courses