Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders

Autores
Perl, Yonatan Sanz; Bocaccio, Hernán; Pérez Ipiña, Ignacio; Zamberlán, Federico; Piccinini, Juan Ignacio; Laufs, Helmut; Kringelbach, Morten; Deco, Gustavo; Tagliazucchi, Enzo Rodolfo
Año de publicación
2020
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
We consider the problem of encoding pairwise correlations between coupled dynamical systems in a low-dimensional latent space based on few distinct observations. We use variational autoencoders (VAEs) to embed temporal correlations between coupled nonlinear oscillators that model brain states in the wake-sleep cycle into a two-dimensional manifold. Training a VAE with samples generated using two different parameter combinations results in an embedding that encodes the repertoire of collective dynamics, as well as the topology of the underlying connectivity network. We first follow this approach to infer the trajectory of brain states measured from wakefulness to deep sleep from the two end points of this trajectory; then, we show that the same architecture was capable of representing the pairwise correlations of generic Landau-Stuart oscillators coupled by complex network topology.
Fil: Perl, Yonatan Sanz. Universidad de San Andrés; Argentina. Universitat Pompeu Fabra; España. Universidad de Buenos Aires; Argentina
Fil: Bocaccio, Hernán. Universidad de Buenos Aires; Argentina
Fil: Pérez Ipiña, Ignacio. Universidad de Buenos Aires; Argentina
Fil: Zamberlán, Federico. Universidad de Buenos Aires; Argentina
Fil: Piccinini, Juan Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
Fil: Laufs, Helmut. Christian-Albrechts-University Kiel; Alemania
Fil: Kringelbach, Morten. University of Oxford; Reino Unido
Fil: Deco, Gustavo. Universitat Pompeu Fabra; España
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
Materia
Autoencoders
Dynamics
Consciousness
Machine Learning
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:11336/146026
Acceder
id CONICETDig_eaab0f3822bc522e4a82dae3ed532703
oai_identifier_str oai:ri.conicet.gov.ar:11336/146026
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Generative Embeddings of Brain Collective Dynamics Using Variational AutoencodersPerl, Yonatan SanzBocaccio, HernánPérez Ipiña, IgnacioZamberlán, FedericoPiccinini, Juan IgnacioLaufs, HelmutKringelbach, MortenDeco, GustavoTagliazucchi, Enzo RodolfoAutoencodersDynamicsConsciousnessMachine Learninghttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1We consider the problem of encoding pairwise correlations between coupled dynamical systems in a low-dimensional latent space based on few distinct observations. We use variational autoencoders (VAEs) to embed temporal correlations between coupled nonlinear oscillators that model brain states in the wake-sleep cycle into a two-dimensional manifold. Training a VAE with samples generated using two different parameter combinations results in an embedding that encodes the repertoire of collective dynamics, as well as the topology of the underlying connectivity network. We first follow this approach to infer the trajectory of brain states measured from wakefulness to deep sleep from the two end points of this trajectory; then, we show that the same architecture was capable of representing the pairwise correlations of generic Landau-Stuart oscillators coupled by complex network topology.Fil: Perl, Yonatan Sanz. Universidad de San Andrés; Argentina. Universitat Pompeu Fabra; España. Universidad de Buenos Aires; ArgentinaFil: Bocaccio, Hernán. Universidad de Buenos Aires; ArgentinaFil: Pérez Ipiña, Ignacio. Universidad de Buenos Aires; ArgentinaFil: Zamberlán, Federico. Universidad de Buenos Aires; ArgentinaFil: Piccinini, Juan Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; ArgentinaFil: Laufs, Helmut. Christian-Albrechts-University Kiel; AlemaniaFil: Kringelbach, Morten. University of Oxford; Reino UnidoFil: Deco, Gustavo. Universitat Pompeu Fabra; EspañaFil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; ArgentinaAmerican Physical Society2020-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/146026Perl, Yonatan Sanz; Bocaccio, Hernán; Pérez Ipiña, Ignacio; Zamberlán, Federico; Piccinini, Juan Ignacio; et al.; Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders; American Physical Society; Physical Review Letters; 125; 23; 12-2020; 1-60031-9007CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1103/PhysRevLett.125.238101info:eu-repo/semantics/altIdentifier/url/https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.125.238101info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-10T13:24:35Zoai:ri.conicet.gov.ar:11336/146026instacron: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 13:24:35.763CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
title Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
spellingShingle Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
Perl, Yonatan Sanz
Autoencoders
Dynamics
Consciousness
Machine Learning
title_short Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
title_full Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
title_fullStr Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
title_full_unstemmed Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
title_sort Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders
dc.creator.none.fl_str_mv Perl, Yonatan Sanz
Bocaccio, Hernán
Pérez Ipiña, Ignacio
Zamberlán, Federico
Piccinini, Juan Ignacio
Laufs, Helmut
Kringelbach, Morten
Deco, Gustavo
Tagliazucchi, Enzo Rodolfo
author Perl, Yonatan Sanz
author_facet Perl, Yonatan Sanz
Bocaccio, Hernán
Pérez Ipiña, Ignacio
Zamberlán, Federico
Piccinini, Juan Ignacio
Laufs, Helmut
Kringelbach, Morten
Deco, Gustavo
Tagliazucchi, Enzo Rodolfo
author_role author
author2 Bocaccio, Hernán
Pérez Ipiña, Ignacio
Zamberlán, Federico
Piccinini, Juan Ignacio
Laufs, Helmut
Kringelbach, Morten
Deco, Gustavo
Tagliazucchi, Enzo Rodolfo
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Autoencoders
Dynamics
Consciousness
Machine Learning
topic Autoencoders
Dynamics
Consciousness
Machine Learning
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv We consider the problem of encoding pairwise correlations between coupled dynamical systems in a low-dimensional latent space based on few distinct observations. We use variational autoencoders (VAEs) to embed temporal correlations between coupled nonlinear oscillators that model brain states in the wake-sleep cycle into a two-dimensional manifold. Training a VAE with samples generated using two different parameter combinations results in an embedding that encodes the repertoire of collective dynamics, as well as the topology of the underlying connectivity network. We first follow this approach to infer the trajectory of brain states measured from wakefulness to deep sleep from the two end points of this trajectory; then, we show that the same architecture was capable of representing the pairwise correlations of generic Landau-Stuart oscillators coupled by complex network topology.
Fil: Perl, Yonatan Sanz. Universidad de San Andrés; Argentina. Universitat Pompeu Fabra; España. Universidad de Buenos Aires; Argentina
Fil: Bocaccio, Hernán. Universidad de Buenos Aires; Argentina
Fil: Pérez Ipiña, Ignacio. Universidad de Buenos Aires; Argentina
Fil: Zamberlán, Federico. Universidad de Buenos Aires; Argentina
Fil: Piccinini, Juan Ignacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
Fil: Laufs, Helmut. Christian-Albrechts-University Kiel; Alemania
Fil: Kringelbach, Morten. University of Oxford; Reino Unido
Fil: Deco, Gustavo. Universitat Pompeu Fabra; España
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
description We consider the problem of encoding pairwise correlations between coupled dynamical systems in a low-dimensional latent space based on few distinct observations. We use variational autoencoders (VAEs) to embed temporal correlations between coupled nonlinear oscillators that model brain states in the wake-sleep cycle into a two-dimensional manifold. Training a VAE with samples generated using two different parameter combinations results in an embedding that encodes the repertoire of collective dynamics, as well as the topology of the underlying connectivity network. We first follow this approach to infer the trajectory of brain states measured from wakefulness to deep sleep from the two end points of this trajectory; then, we show that the same architecture was capable of representing the pairwise correlations of generic Landau-Stuart oscillators coupled by complex network topology.
publishDate 2020
dc.date.none.fl_str_mv 2020-12
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/11336/146026
Perl, Yonatan Sanz; Bocaccio, Hernán; Pérez Ipiña, Ignacio; Zamberlán, Federico; Piccinini, Juan Ignacio; et al.; Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders; American Physical Society; Physical Review Letters; 125; 23; 12-2020; 1-6
0031-9007
CONICET Digital
CONICET
url http://hdl.handle.net/11336/146026
identifier_str_mv Perl, Yonatan Sanz; Bocaccio, Hernán; Pérez Ipiña, Ignacio; Zamberlán, Federico; Piccinini, Juan Ignacio; et al.; Generative Embeddings of Brain Collective Dynamics Using Variational Autoencoders; American Physical Society; Physical Review Letters; 125; 23; 12-2020; 1-6
0031-9007
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1103/PhysRevLett.125.238101
info:eu-repo/semantics/altIdentifier/url/https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.125.238101
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
dc.publisher.none.fl_str_mv American Physical Society
publisher.none.fl_str_mv American Physical Society
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_ 1842981365100838912
score 12.48226

Publicaciones similares