Minimalist neural networks training for phase classification in diluted Ising models

Autores
Garcia Pavioni, G. L.; Lamas, Carlos Alberto; Arlego, Marcelo José Fabián
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In this article, we explore the potential of artificial neural networks, which are trained using an exceptionally simplified catalog of ideal configurations encompassing both order and disorder. We explore the generalization power of these networks to classify phases in complex models that are far from the simplified training context.As a paradigmatic case, we analyze the order–disorder transition of the diluted Ising model on several two-dimensional crystalline lattices, which does not have an exact solution and presents challenges for most of the available analytical and numerical techniques. Quantitative agreement is obtained in the determination of transition temperatures and percolation densities, with comparatively much more expensive methods. These findings highlight the potential of minimalist training in neural networks to describe complex phenomena and have implications beyond condensed matter physics.
Fil: Garcia Pavioni, G. L.. Universidad Nacional de La Plata. Facultad de Ciencias Exactas; Argentina
Fil: Lamas, Carlos Alberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; Argentina
Fil: Arlego, Marcelo José Fabián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; Argentina
Materia
Minimalist
Neural
Network
Training
Phase
Classification
Diluted
Ising
Models
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/257344
Acceder
id CONICETDig_e47f14e45e99a0b5f719eeb4bcade4c5
oai_identifier_str oai:ri.conicet.gov.ar:11336/257344
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Minimalist neural networks training for phase classification in diluted Ising modelsGarcia Pavioni, G. L.Lamas, Carlos AlbertoArlego, Marcelo José FabiánMinimalistNeuralNetworkTrainingPhaseClassificationDilutedIsingModelshttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1In this article, we explore the potential of artificial neural networks, which are trained using an exceptionally simplified catalog of ideal configurations encompassing both order and disorder. We explore the generalization power of these networks to classify phases in complex models that are far from the simplified training context.As a paradigmatic case, we analyze the order–disorder transition of the diluted Ising model on several two-dimensional crystalline lattices, which does not have an exact solution and presents challenges for most of the available analytical and numerical techniques. Quantitative agreement is obtained in the determination of transition temperatures and percolation densities, with comparatively much more expensive methods. These findings highlight the potential of minimalist training in neural networks to describe complex phenomena and have implications beyond condensed matter physics.Fil: Garcia Pavioni, G. L.. Universidad Nacional de La Plata. Facultad de Ciencias Exactas; ArgentinaFil: Lamas, Carlos Alberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; ArgentinaFil: Arlego, Marcelo José Fabián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; ArgentinaElsevier2024-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/257344Garcia Pavioni, G. L.; Lamas, Carlos Alberto; Arlego, Marcelo José Fabián; Minimalist neural networks training for phase classification in diluted Ising models; Elsevier; Computational Materials Science; 235; 112792; 1-2024; 1-100927-0256CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.commatsci.2024.112792info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/abs/pii/S0927025624000132info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-10T13:13:56Zoai:ri.conicet.gov.ar:11336/257344instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-10 13:13:56.53CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Minimalist neural networks training for phase classification in diluted Ising models
title Minimalist neural networks training for phase classification in diluted Ising models
spellingShingle Minimalist neural networks training for phase classification in diluted Ising models
Garcia Pavioni, G. L.
Minimalist
Neural
Network
Training
Phase
Classification
Diluted
Ising
Models
title_short Minimalist neural networks training for phase classification in diluted Ising models
title_full Minimalist neural networks training for phase classification in diluted Ising models
title_fullStr Minimalist neural networks training for phase classification in diluted Ising models
title_full_unstemmed Minimalist neural networks training for phase classification in diluted Ising models
title_sort Minimalist neural networks training for phase classification in diluted Ising models
dc.creator.none.fl_str_mv Garcia Pavioni, G. L.
Lamas, Carlos Alberto
Arlego, Marcelo José Fabián
author Garcia Pavioni, G. L.
author_facet Garcia Pavioni, G. L.
Lamas, Carlos Alberto
Arlego, Marcelo José Fabián
author_role author
author2 Lamas, Carlos Alberto
Arlego, Marcelo José Fabián
author2_role author
author
dc.subject.none.fl_str_mv Minimalist
Neural
Network
Training
Phase
Classification
Diluted
Ising
Models
topic Minimalist
Neural
Network
Training
Phase
Classification
Diluted
Ising
Models
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv In this article, we explore the potential of artificial neural networks, which are trained using an exceptionally simplified catalog of ideal configurations encompassing both order and disorder. We explore the generalization power of these networks to classify phases in complex models that are far from the simplified training context.As a paradigmatic case, we analyze the order–disorder transition of the diluted Ising model on several two-dimensional crystalline lattices, which does not have an exact solution and presents challenges for most of the available analytical and numerical techniques. Quantitative agreement is obtained in the determination of transition temperatures and percolation densities, with comparatively much more expensive methods. These findings highlight the potential of minimalist training in neural networks to describe complex phenomena and have implications beyond condensed matter physics.
Fil: Garcia Pavioni, G. L.. Universidad Nacional de La Plata. Facultad de Ciencias Exactas; Argentina
Fil: Lamas, Carlos Alberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; Argentina
Fil: Arlego, Marcelo José Fabián. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física La Plata; Argentina
description In this article, we explore the potential of artificial neural networks, which are trained using an exceptionally simplified catalog of ideal configurations encompassing both order and disorder. We explore the generalization power of these networks to classify phases in complex models that are far from the simplified training context.As a paradigmatic case, we analyze the order–disorder transition of the diluted Ising model on several two-dimensional crystalline lattices, which does not have an exact solution and presents challenges for most of the available analytical and numerical techniques. Quantitative agreement is obtained in the determination of transition temperatures and percolation densities, with comparatively much more expensive methods. These findings highlight the potential of minimalist training in neural networks to describe complex phenomena and have implications beyond condensed matter physics.
publishDate 2024
dc.date.none.fl_str_mv 2024-01
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/257344
Garcia Pavioni, G. L.; Lamas, Carlos Alberto; Arlego, Marcelo José Fabián; Minimalist neural networks training for phase classification in diluted Ising models; Elsevier; Computational Materials Science; 235; 112792; 1-2024; 1-10
0927-0256
CONICET Digital
CONICET
url http://hdl.handle.net/11336/257344
identifier_str_mv Garcia Pavioni, G. L.; Lamas, Carlos Alberto; Arlego, Marcelo José Fabián; Minimalist neural networks training for phase classification in diluted Ising models; Elsevier; Computational Materials Science; 235; 112792; 1-2024; 1-10
0927-0256
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.commatsci.2024.112792
info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/abs/pii/S0927025624000132
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842980741203361792
score 12.993085

Publicaciones similares