Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2001 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/101351 |
Resumo: | The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks are derived and studied in replica-symmetric mean-field theory generalizing earlier works on either the fully connected or the symmetrical extremely diluted network. Capacity-gain parameter phase diagrams are obtained for the Q=3, Q=4, and Q=∞ state networks with uniformly distributed patterns of low activity in order to search for the effects of a gradual dilution of the synapses. It is shown that enlarged regions of continuous changeover into a region of optimal performance are obtained for finite stochastic noise and small but finite connectivity. The de Almeida-Thouless lines of stability are obtained for arbitrary connectivity, and the resulting phase diagrams are used to draw conclusions on the behavior of symmetrically diluted networks with other pattern distributions of either high or low activity. |
id |
UFRGS-2_964984d7e00db8cd51aa2c11292709e3 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/101351 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Theumann, Walter KarlErichsen Junior, Rubem2014-08-19T02:10:23Z20011539-3755http://hdl.handle.net/10183/101351000308530The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks are derived and studied in replica-symmetric mean-field theory generalizing earlier works on either the fully connected or the symmetrical extremely diluted network. Capacity-gain parameter phase diagrams are obtained for the Q=3, Q=4, and Q=∞ state networks with uniformly distributed patterns of low activity in order to search for the effects of a gradual dilution of the synapses. It is shown that enlarged regions of continuous changeover into a region of optimal performance are obtained for finite stochastic noise and small but finite connectivity. The de Almeida-Thouless lines of stability are obtained for arbitrary connectivity, and the resulting phase diagrams are used to draw conclusions on the behavior of symmetrically diluted networks with other pattern distributions of either high or low activity.application/pdfengPhysical review. E, Statistical, nonlinear, and soft matter physics. Vol. 64, no. 6 pt. 1 (Dec. 2001), 061902, 11 p.Redes neuraisDiagramas de faseEstabilidadePropriedades termodinâmicasRetrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networksEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL000308530.pdf000308530.pdfTexto completo (inglês)application/pdf132648http://www.lume.ufrgs.br/bitstream/10183/101351/1/000308530.pdf209b917772e8c8ad873b35607b090d38MD51TEXT000308530.pdf.txt000308530.pdf.txtExtracted Texttext/plain46741http://www.lume.ufrgs.br/bitstream/10183/101351/2/000308530.pdf.txtb406b9b588c8751721081b7178c7175cMD52THUMBNAIL000308530.pdf.jpg000308530.pdf.jpgGenerated Thumbnailimage/jpeg1990http://www.lume.ufrgs.br/bitstream/10183/101351/3/000308530.pdf.jpg4d2881d08a86814af4e48621ad4e9417MD5310183/1013512018-10-22 09:19:39.274oai:www.lume.ufrgs.br:10183/101351Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2018-10-22T12:19:39Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
title |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
spellingShingle |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks Theumann, Walter Karl Redes neurais Diagramas de fase Estabilidade Propriedades termodinâmicas |
title_short |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
title_full |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
title_fullStr |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
title_full_unstemmed |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
title_sort |
Retrieval behavior and thermodynamic properties of symmetrically diluted Q-ising neural networks |
author |
Theumann, Walter Karl |
author_facet |
Theumann, Walter Karl Erichsen Junior, Rubem |
author_role |
author |
author2 |
Erichsen Junior, Rubem |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Theumann, Walter Karl Erichsen Junior, Rubem |
dc.subject.por.fl_str_mv |
Redes neurais Diagramas de fase Estabilidade Propriedades termodinâmicas |
topic |
Redes neurais Diagramas de fase Estabilidade Propriedades termodinâmicas |
description |
The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks are derived and studied in replica-symmetric mean-field theory generalizing earlier works on either the fully connected or the symmetrical extremely diluted network. Capacity-gain parameter phase diagrams are obtained for the Q=3, Q=4, and Q=∞ state networks with uniformly distributed patterns of low activity in order to search for the effects of a gradual dilution of the synapses. It is shown that enlarged regions of continuous changeover into a region of optimal performance are obtained for finite stochastic noise and small but finite connectivity. The de Almeida-Thouless lines of stability are obtained for arbitrary connectivity, and the resulting phase diagrams are used to draw conclusions on the behavior of symmetrically diluted networks with other pattern distributions of either high or low activity. |
publishDate |
2001 |
dc.date.issued.fl_str_mv |
2001 |
dc.date.accessioned.fl_str_mv |
2014-08-19T02:10:23Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/101351 |
dc.identifier.issn.pt_BR.fl_str_mv |
1539-3755 |
dc.identifier.nrb.pt_BR.fl_str_mv |
000308530 |
identifier_str_mv |
1539-3755 000308530 |
url |
http://hdl.handle.net/10183/101351 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Physical review. E, Statistical, nonlinear, and soft matter physics. Vol. 64, no. 6 pt. 1 (Dec. 2001), 061902, 11 p. |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/101351/1/000308530.pdf http://www.lume.ufrgs.br/bitstream/10183/101351/2/000308530.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/101351/3/000308530.pdf.jpg |
bitstream.checksum.fl_str_mv |
209b917772e8c8ad873b35607b090d38 b406b9b588c8751721081b7178c7175c 4d2881d08a86814af4e48621ad4e9417 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801224845688569856 |