On-line learning in a discrete state space

Simple item page
dc.creatorKinzel, W.
dc.creatorUrbanczik, R.
dc.date1997-05-26
dc.date.accessioned2026-07-07T03:09:04Z
dc.date.available2026-07-07T03:09:04Z
dc.descriptionOn-line learning of a rule given by an N-dimensional Ising perceptron, is considered for the case when the student is constrained to take values in a discrete state space of size $L^N$. For L=2 no on-line algorithm can achieve a finite overlap with the teacher in the thermodynamic limit. However, if $L$ is on the order of $\sqrt{N}$, Hebbian learning does achieve a finite overlap.
dc.description7 pages, 1 Figure, Latex, submitted to J.Phys.A
dc.identifierhttps://arxiv.org/abs/cond-mat/9705257
dc.identifierhttp://arxiv.org/abs/cond-mat/9705257
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/27742
dc.subjectCondensed Matter
dc.titleOn-line learning in a discrete state space
dc.typetext

Files

Collections

arXiv