Robust Boosting for Learning from Few Examples
Abstract
The authors present and analyze a novel regularization technique based on enhancing their data set with corrupted copies of their original data. The motivation is that since the learning algorithm lacks information about which parts of the data are reliable, it has to make more robust classification functions. Using this framework, they propose a simple addition to the gentle boosting algorithm that enables it to work with only a few examples. They test this new algorithm on a variety of data sets and show convincing results.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2006
- Accession Number
- ADA455241
Entities
People
- Ian Martin
- Lior Wolf
Organizations
- Massachusetts Institute of Technology