Show simple item record

dc.contributor.authorErichsen Junior, Rubempt_BR
dc.contributor.authorTheumann, Walter Karlpt_BR
dc.contributor.authorDominguez, David Renato Carretapt_BR
dc.date.accessioned2014-08-19T02:10:10Zpt_BR
dc.date.issued1999pt_BR
dc.identifier.issn1063-651Xpt_BR
dc.identifier.urihttp://hdl.handle.net/10183/101307pt_BR
dc.description.abstractThe categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multistate patterns in a two level structure of ancestors and descendents ~examples! are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q=3-state model and a Q=∞ state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The categorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained. [S1063-651X(99)09212-0]en
dc.format.mimetypeapplication/pdf
dc.language.isoengpt_BR
dc.relation.ispartofPhysical Review. E, Statistical Physics, Plasmas, Fluids and Related Interdisciplinary Topics. New York. Vol. 60, no. 6, pt. B (Dec. 1999), p. 7321-7331pt_BR
dc.rightsOpen Accessen
dc.subjectRedes neurais de hopfieldpt_BR
dc.subjectRuídospt_BR
dc.titleCategorization in fully connected multistate neural network modelspt_BR
dc.typeArtigo de periódicopt_BR
dc.identifier.nrb000055631pt_BR
dc.type.originEstrangeiropt_BR


Files in this item

Thumbnail
   

This item is licensed under a Creative Commons License

Show simple item record