Show simple item record

dc.contributor.authorCosta, Rogerio Adeodato Limapt_BR
dc.contributor.authorTheumann, Alba Graciela Rivas dept_BR
dc.date.accessioned2014-09-24T02:12:15Zpt_BR
dc.date.issued2000pt_BR
dc.identifier.issn1063-651Xpt_BR
dc.identifier.urihttp://hdl.handle.net/10183/103710pt_BR
dc.description.abstractWe consider the categorization problem in a Hopfield network with an extensive number of concepts p =αN and trained with s examples of weight λτ, T=1, . . . ,s in the presence of synaptic noise represented by a dimensionless ‘‘temperature’’ T. We find that the retrieval capacity of an example with weight λ₁, and the corresponding categorization error, depend also on the arithmetic mean λm of the other weights. The categorization process is similar to that in a network trained with Hebb’s rule, but for λ₁/λm>1 the retrieval phase is enhanced. We present the phase diagram in the T-α plane, together with the de Almeida–Thouless line of instability. The phase diagrams in the α-s plane are discussed in the absence of synaptic noise and several values of the correlation parameter b.en
dc.format.mimetypeapplication/pdf
dc.language.isoengpt_BR
dc.relation.ispartofPhysical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics. Melville. Vol. 61, no. 5B (May 2000), p. 4860-4865pt_BR
dc.rightsOpen Accessen
dc.subjectFenomenos criticospt_BR
dc.subjectRedes neurais de hopfieldpt_BR
dc.subjectAprendendo por exemplopt_BR
dc.subjectTransições magnéticaspt_BR
dc.titleCategorization in a Hopfield network trained with weighted examples : extensive number of conceptspt_BR
dc.typeArtigo de periódicopt_BR
dc.identifier.nrb000275730pt_BR
dc.type.originEstrangeiropt_BR


Files in this item

Thumbnail
   

This item is licensed under a Creative Commons License

Show simple item record