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

Simple item page
dc.creatorVicente, Renato
dc.creatorKinouchi, Osame
dc.creatorCaticha, Nestor
dc.date1998-01-28
dc.date.accessioned2026-07-07T03:09:52Z
dc.date.available2026-07-07T03:09:52Z
dc.descriptionWe 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.
dc.description24 pages, 8 figures, to appear in Machine Learning Journal
dc.identifierhttps://arxiv.org/abs/cond-mat/9801297
dc.identifierhttp://arxiv.org/abs/cond-mat/9801297
dc.identifierMachine Learning 32 179-201 (1998)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/28057
dc.subjectDisordered Systems and Neural Networks
dc.subjectStatistical Mechanics
dc.titleStatistical Mechanics of Online Learning of Drifting Concepts : A Variational Approach
dc.typetext

Files

Collections

arXiv