Neural Networks Processing Mean Values of Random Variables

Simple item page
dc.creatorBarber, M. J.
dc.creatorClark, J. W.
dc.creatorAnderson, C. H.
dc.date2004-07-16
dc.date.accessioned2026-07-07T02:59:14Z
dc.date.available2026-07-07T02:59:14Z
dc.descriptionWe introduce a class of neural networks derived from probabilistic models in the form of Bayesian belief networks. By imposing additional assumptions about the nature of the probabilistic models represented in the belief networks, we derive neural networks with standard dynamics that require no training to determine the synaptic weights, that can pool multiple sources of evidence, and that deal cleanly and consistently with inconsistent or contradictory evidence. The presented neural networks capture many properties of Bayesian belief networks, providing distributed versions of probabilistic models.
dc.description7 pages, 3 figures, 1 table, submitted to Phys Rev E
dc.identifierhttps://arxiv.org/abs/cond-mat/0407436
dc.identifierhttp://arxiv.org/abs/cond-mat/0407436
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/24435
dc.subjectDisordered Systems and Neural Networks
dc.titleNeural Networks Processing Mean Values of Random Variables
dc.typetext

Files

Collections

arXiv