Prof. Dmitry Panchenko
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.
OCW has published multiple versions of this subject.
Panchenko, Dmitry. 18.465 Topics in Statistics: Statistical Learning Theory, Spring 2007. (MIT OpenCourseWare: Massachusetts Institute of Technology), http://ocw.mit.edu/courses/mathematics/18-465-topics-in-statistics-statistical-learning-theory-spring-2007 (Accessed). License: Creative Commons BY-NC-SA