.png){kind=icon}
.png){kind=icon}
Return
Learning stochastic dynamics and predicting emergent behavior using transformers
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-024-45629-w.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. Learning the dynamics governing a simulation or experiment usually requires coarse graining or projection, as the number of transition rates typically grows exponentially with system size. The authors show that transformers, neural networks introduced initially for natural language processing, can be used to parameterize the dynamics of large systems without coarse graining.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.7
Papers:
9.2W
Citations:
91.2W