Statistical Features in Learning

dc.creatorStamatescu, Ion-Olimpiu
dc.date1998-09-09
dc.date1998-09-30
dc.date.accessioned2026-07-07T03:11:30Z
dc.date.available2026-07-07T03:11:30Z
dc.descriptionWe study some features of learning models based on "delayed" and undifferentiated reinforcement and realized by simple algorithms which may be considered of a very elementary nature. We show that a modification of the Hebb-rule works well for this problem in a neural network realization and study numerically its convergence properties. An illustration for a more "concrete" situation is provided.
dc.description13 pages, 7 figures; LEARNING'98 Madrid; 2 notations, 1 typo corrected
dc.identifierhttps://arxiv.org/abs/cond-mat/9809135
dc.identifierhttp://arxiv.org/abs/cond-mat/9809135
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/28597
dc.subjectCondensed Matter
dc.subjectAdaptation and Self-Organizing Systems
dc.titleStatistical Features in Learning
dc.typetext

Files

Collections