Machine Learning Summer School 2005 - Chicago

Boosting

author: Robert Schapire, Princeton University

Description

Boosting is a general method for producing a very accurate classification rule by combining rough and moderately inaccurate "rules of thumb." While rooted in a theoretical framework of machine learning, boosting has been found to perform quite well empirically. This tutorial will introduce the boosting algorithm AdaBoost?, and explain the underlying theory of boosting, including explanations that have been given as to why boosting often does not suffer from overfitting, as well as some of the myriad other theoretical points of view that have been taken on this algorithm. Some recent applications and extensions of boosting will also be described.

Categories

Top: Computer Science: Machine Learning: Boosting

You might be experiencing some problems with Your Video player.

*Slides*
0:00	A Boosting TutoriA Tutorial
0:08	Example: “HowMay I Help IHelp You?”
3:16	The Boosting Approach
4:18	Details
5:03	Boosting
7:04	Outline of Tutorial
7:27	Brief BackgrounBrief Background
7:33	The Boosting Problem
9:43	Early Boosting Algorithms
10:32	AdaBoost
10:52	Basic Algorithm and Core Theory
11:31	A Formal Description of Boosting
16:02	AdaBoost
20:01	Toy Example
20:34	Round 1
21:31	Round 2
22:41	Round 3
23:17	Final Classifier
28:19	Analyzing the training error
33:22	Proof
34:33	Proof (cont.)
37:16	Proof (cont.)
38:18	How Will Test Error Behave? (A First First Guess)
41:03	Actual Typical Typical Run
52:03	A Better Story: Theory of Margins
55:39	Empirical Evidence: The Margin Distribution
59:57	Theoretical Evidence:Analyzing Boosting Using Margins

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.