Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/305310
COMPARTIR / EXPORTAR:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatiotemporal systems using scalable neural networks |
Autor: | Goldmann, Mirko; Mirasso, Claudio R. CSIC ORCID ; Fischer, Ingo CSIC ORCID ; Soriano, Miguel C. | Fecha de publicación: | 21-oct-2022 | Editor: | American Physical Society | Citación: | Physical Review E 106: 044211 (2022) | Resumen: | We design scalable neural networks adapted to translational symmetries in dynamical systems, capable of inferring untrained high-dimensional dynamics for different system sizes. We train these networks to predict the dynamics of delay-dynamical and spatiotemporal systems for a single size. Then, we drive the networks by their own predictions. We demonstrate that by scaling the size of the trained network, we can predict the complex dynamics for larger or smaller system sizes. Thus, the network learns from a single example and by exploiting symmetry properties infers entire bifurcation diagrams. | Versión del editor: | https://doi.org/10.1103/PhysRevE.106.044211 | URI: | http://hdl.handle.net/10261/305310 | DOI: | 10.1103/PhysRevE.106.044211 | ISSN: | 2470-0045 | E-ISSN: | 2470-0053 | Referencias: | Goldmann, Mirko; Mirasso, Claudio R.; Fischer, Ingo; Soriano, Miguel C.; 2022; Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatio-temporal systems using scalable neural networks [Preprint]; arXiv; Version 2; https://doi.org/10.48550/arXiv.2111.03706 |
Aparece en las colecciones: | (IFISC) Artículos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
scalable-neural-networks.pdf | 7,38 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
SCOPUSTM
Citations
4
checked on 08-may-2024
WEB OF SCIENCETM
Citations
1
checked on 25-feb-2024
Page view(s)
47
checked on 14-may-2024
Download(s)
53
checked on 14-may-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.