Learning and generalization theories of large committee--machines

dc.creatorMonasson, Remi
dc.creatorZecchina, Riccardo
dc.date1996-01-25
dc.date.accessioned2026-07-07T03:08:10Z
dc.date.available2026-07-07T03:08:10Z
dc.descriptionThe study of the distribution of volumes associated to the internal representations of learning examples allows us to derive the critical learning capacity ($α_c=\frac{16}π \sqrt{\ln K}$) of large committee machines, to verify the stability of the solution in the limit of a large number $K$ of hidden units and to find a Bayesian generalization cross--over at $α=K$.
dc.description14 pages, revtex
dc.identifierhttps://arxiv.org/abs/cond-mat/9601122
dc.identifierhttp://arxiv.org/abs/cond-mat/9601122
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/27452
dc.subjectCondensed Matter
dc.titleLearning and generalization theories of large committee--machines
dc.typetext

Files

Collections