Your browser doesn't support javascript.
loading
Learning stochastic dynamics and predicting emergent behavior using transformers.
Casert, Corneel; Tamblyn, Isaac; Whitelam, Stephen.
Afiliación
  • Casert C; Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA, 94720, USA. ccasert@lbl.gov.
  • Tamblyn I; Department of Physics and Astronomy, Ghent University, 9000, Ghent, Belgium. ccasert@lbl.gov.
  • Whitelam S; Cash App, Block, Toronto, ON, M5A 1J7, Canada. isaac.tamblyn@uottawa.ca.
Nat Commun ; 15(1): 1875, 2024 Feb 29.
Article en En | MEDLINE | ID: mdl-38424071
ABSTRACT
We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training. We consider a lattice model of active matter undergoing continuous-time Monte Carlo dynamics, simulated at a density at which its steady state comprises small, dispersed clusters. We train a neural network called a transformer on a single trajectory of the model. The transformer, which we show has the capacity to represent dynamical rules that are numerous and nonlocal, learns that the dynamics of this model consists of a small number of processes. Forward-propagated trajectories of the trained transformer, at densities not encountered during training, exhibit motility-induced phase separation and so predict the existence of a nonequilibrium phase transition. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space, and so the procedure used here can be applied to a wide range of physical systems, including those with large and complex dynamical generators.

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Reino Unido