Agnostic Active Learning

Posted in Companies, Science on September 12, 2008

Agnostic Active Learning

The great promise of active learning is that via interaction the number of samples required can be reduced to logarithmic in the number required for standard batch supervised learning methods. To achieve this promise, active learning must be able to cope with noisy data. We show how it is possible to cope with even malicious noise in an active learning setting, removing noise an obstacle to regular application of active learning.

Author: John Langford, Yahoo Research, Yahoo!

Watch Video

Tags: Yahoo!, Science, Lectures, Computer Science, Machine Learning, VideoLectures.Net, Active Learning