Welcome to the UPF Digital Repository

Generative embeddings of brain collective dynamics using variational autoencoders

Show simple item record

dc.contributor.author Sanz Perl, Yonatan
dc.contributor.author Bocaccio, Hernán
dc.contributor.author Pérez-Ipiña, Ignacio
dc.contributor.author Zamberlán, Federico
dc.contributor.author Piccinini, Juan
dc.contributor.author Laufs, Helmut
dc.contributor.author Kringelbach, Morten L.
dc.contributor.author Deco, Gustavo
dc.contributor.author Tagliazucchi, Enzo
dc.date.accessioned 2021-03-22T08:37:33Z
dc.date.available 2021-03-22T08:37:33Z
dc.date.issued 2020
dc.identifier.citation Perl YS, Bocaccio H, Pérez-Ipiña I, Zamberlán F, Piccinini J, Laufs H, Kringelbach M, Deco G, Tagliazucchi E. Generative embeddings of brain collective dynamics using variational autoencoders. Phys Rev Lett. 2020 Dec 4;125(23):238101. DOI: 10.1103/PhysRevLett.125.238101
dc.identifier.issn 0031-9007
dc.identifier.uri http://hdl.handle.net/10230/46878
dc.description.abstract 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.
dc.description.sponsorship Authors acknowledge funding from Agencia Nacional De Promocion Cientifica Y Tecnologica (Argentina), Grant No. PICT-2018-03103.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher American Physical Society
dc.relation.ispartof Phys Rev Lett. 2020 Dec 4;125(23):238101
dc.rights © American Physical Society. Published article available at https://doi.org/10.1103/PhysRevLett.125.238101
dc.title Generative embeddings of brain collective dynamics using variational autoencoders
dc.type info:eu-repo/semantics/article
dc.identifier.doi http://dx.doi.org/10.1103/PhysRevLett.125.238101
dc.subject.keyword Patterns in complex systems
dc.subject.keyword Neural encoding
dc.subject.keyword Neuroscience
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account


In collaboration with Compliant to Partaking