Deep learning for universal linear embeddings of nonlinear dynamics
It is often advantageous to transform a strongly nonlinear system into a linear one in order to simplify its analysis for prediction and control. Here the authors combine dynamical systems with deep learning to identify these hard-to-find transformations.
Guardado en:
Autores principales: | Bethany Lusch, J. Nathan Kutz, Steven L. Brunton |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2018
|
Materias: | |
Acceso en línea: | https://doaj.org/article/d72f7d260a5d4c2a905fed768a9492b8 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
DeepGreen: deep learning of Green’s functions for nonlinear boundary value problems
por: Craig R. Gin, et al.
Publicado: (2021) -
Chaos as an intermittently forced linear system
por: Steven L. Brunton, et al.
Publicado: (2017) -
Learning dominant physical processes with data-driven balance models
por: Jared L. Callaham, et al.
Publicado: (2021) -
Irrelevance of linear controllability to nonlinear dynamical networks
por: Junjie Jiang, et al.
Publicado: (2019) -
Embeddings from deep learning transfer GO annotations beyond homology
por: Maria Littmann, et al.
Publicado: (2021)