stanford.seal64.gif (1,768 bytes)

Broad Area Colloquium for Artificial Intelligence,
Geometry, Graphics, Robotics and Vision

The Boosting Approach to Machine Learning

Robert Schapire
AT&T Labs

Monday, April 29th, 2002, 4:45PM
Gates B01


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. In this talk, I will introduce the boosting algorithm AdaBoost, and explain the underlying theory of boosting, including our explanation of why boosting often does not suffer from overfitting. I also will describe some recent applications and extensions of boosting, including an application to a human-computer spoken-dialogue system.

About the Speaker

Robert Schapire received his ScB in math and computer science from Brown University in 1986, and his SM (1988) and PhD (1991) from MIT under the supervision of Ronald Rivest. His dissertation on "The Design and Analysis of Efficient Learning Algorithms" won the 1991 ACM Doctoral Dissertation Award. After a short post-doc at Harvard, Rob became a member of technical staff at AT&T Labs (formerly AT&T Bell Laboratories) where he has been since 1991. His main research interest is in theoretical and applied machine learning.

Back to the Colloquium Page