Accession Number:

ADA455241

Title:

Robust Boosting for Learning from Few Examples

Descriptive Note:

Research paper

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE MA CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING

Personal Author(s):

• Wolf, Lior
• Martin, Ian

Report Date:

2006-01-01

Pagination or Media Count:

7.0

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.

Descriptors:

• *ALGORITHMS
• *TARGET RECOGNITION
• *LEARNING MACHINES
• *CLASSIFICATION
• *FEATURE EXTRACTION
• *LINEAR REGRESSION ANALYSIS
• *LEAST SQUARES METHOD
• DATA BASES
• DECOMPOSITION
• TARGET DETECTION
• TRANSFORMATIONS(MATHEMATICS)
• MATHEMATICAL PREDICTION
• DEGREES OF FREEDOM
• TRAINING
• MATRICES(MATHEMATICS)

Subject Categories:

• Statistics and Probability
• Cybernetics
• Target Direction, Range and Position Finding

Distribution Statement:

APPROVED FOR PUBLIC RELEASE