Parametrical Neural Network

Simple item page
dc.creatorKryzhanovsky, B. V.
dc.creatorLitinskii, L. B.
dc.creatorMikaelyan, A. L.
dc.date2002-12-20
dc.date.accessioned2026-07-07T02:48:52Z
dc.date.available2026-07-07T02:48:52Z
dc.descriptionThe storage capacity of the Hopfield model is about 15% of the network size. It can be increased significantly in the Potts-glass model of the associative memory only. In this model neurons can be in more than two different states. We show that even greater storage capacity can be achieved in the parametrical neural network (PNN) that is based on the parametrical four-wave mixing process that is well-known in nonlinear optics. We present a uniform formalism allowing us to describe both PNN and the Potts-glass associative memory. To estimate the storage capacity we use the Chebyshev-Chernov statistical technique.
dc.description16 pages, 2 Postscript figures, sumbitted to Neural Networks
dc.identifierhttps://arxiv.org/abs/cond-mat/0212541
dc.identifierhttp://arxiv.org/abs/cond-mat/0212541
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/20580
dc.subjectDisordered Systems and Neural Networks
dc.subjectQuantitative Biology
dc.titleParametrical Neural Network
dc.typetext

Files

Collections

arXiv