Cargando…
Hierarchical deep learning of multiscale differential equation time-steppers
Nonlinear differential equations rarely admit closed-form solutions, thus requiring numerical time-stepping algorithms to approximate solutions. Further, many systems characterized by multiscale physics exhibit dynamics over a vast range of timescales, making numerical integration expensive. In this...
Autores principales: | Liu, Yuying, Kutz, J. Nathan, Brunton, Steven L. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
The Royal Society
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9207536/ https://www.ncbi.nlm.nih.gov/pubmed/35719073 http://dx.doi.org/10.1098/rsta.2021.0200 |
Ejemplares similares
-
Data-driven discovery of partial differential equations
por: Rudy, Samuel H., et al.
Publicado: (2017) -
Deep learning for universal linear embeddings of nonlinear dynamics
por: Lusch, Bethany, et al.
Publicado: (2018) -
PyNumDiff: A Python package for numerical differentiation of noisy time-series data
por: Van Breugel, Floris, et al.
Publicado: (2022) -
DeepGreen: deep learning of Green’s functions for nonlinear boundary value problems
por: Gin, Craig R., et al.
Publicado: (2021) -
Data-driven discovery of coordinates and governing equations
por: Champion, Kathleen, et al.
Publicado: (2019)