vix.ing · top · new · best · stats · spec

Statistical Mechanics of Online Learning of Drifting Concepts : A Variational Approach

1998/01/28 by Renato Vicente, Osame Kinouchi, Nestor Caticha · 1 citation
Physics and Astronomy · #cond-mat.dis-nn #cond-mat.stat-mech

paper · pdf

published as Machine Learning 32 179-201 (1998) · 24 pages, 8 figures, to appear in Machine Learning Journal

arxiv created 1998/01/28 · arxiv updated 2009/11/30

Abstract

We review the application of Statistical Mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward network learns from examples generated by a time dependent teacher of the same architecture is analyzed. The best possible generalization ability is determined exactly, through the use of a variational method. The constructive variational method also suggests a learning algorithm. It depends, however, on some unavailable quantities, such as the present performance of the student. The construction of estimators for these quantities permits the implementation of a very effective, highly adaptive algorithm. Several other algorithms are also studied for comparison with the optimal bound and the adaptive algorithm, for different types of time evolution of the rule.

Cited by

Related