Field Theoretical Analysis of On-line Learning of Probability Distributions

Simple item page
dc.creatorAida, Toshiaki
dc.date1999-11-30
dc.date.accessioned2026-07-07T12:33:13Z
dc.date.available2026-07-07T12:33:13Z
dc.descriptionOn-line learning of probability distributions is analyzed from the field theoretical point of view. We can obtain an optimal on-line learning algorithm, since renormalization group enables us to control the number of degrees of freedom of a system according to the number of examples. We do not learn parameters of a model, but probability distributions themselves. Therefore, the algorithm requires no a priori knowledge of a model.
dc.description4 pages, 1 figure, RevTex
dc.identifierhttps://arxiv.org/abs/cond-mat/9911474
dc.identifierhttp://arxiv.org/abs/cond-mat/9911474
dc.identifierPhys.Rev.Lett.83:3554-3557,1999
dc.identifierdoi:10.1103/PhysRevLett.83.3554
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/217047
dc.subjectDisordered Systems and Neural Networks
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectHigh Energy Physics - Theory
dc.subjectData Analysis, Statistics and Probability
dc.titleField Theoretical Analysis of On-line Learning of Probability Distributions
dc.typetext

Files

Collections

arXiv