Topics in Statistics: Statistical Learning Theory
18.465 · Mathematics · Graduate · Spring 2007
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.
The syllabus, on MIT OpenCourseWare
The full course — syllabus, assigned readings, problem sets, exams, and lecture notes — lives on OCW. These open the real thing:
Syllabus ↗
Course overview, grading, schedule
Readings ↗
The assigned reading list, session by session
Assignments ↗
Problem sets and projects
Full course on OCW ↗
Everything, including lecture materials
Attribution
Prof. Dmitry Panchenko. 18.465 Topics in Statistics: Statistical Learning Theory. Spring 2007. Massachusetts Institute of Technology: MIT OpenCourseWare, https://ocw.mit.edu. License: CC BY-NC-SA 4.0.
Course materials are © their authors and licensed CC BY-NC-SA 4.0. CurrMana links to the source and does not re-host them.