Cargando…
Elliptic PDE learning is provably data-efficient
Partial differential equations (PDE) learning is an emerging field that combines physics and machine learning to recover unknown physical systems from experimental data. While deep learning models traditionally require copious amounts of training data, recent PDE learning techniques achieve spectacu...
Autores principales: | Boullé, Nicolas, Halikias, Diana, Townsend, Alex |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10523644/ https://www.ncbi.nlm.nih.gov/pubmed/37722063 http://dx.doi.org/10.1073/pnas.2303904120 |
Ejemplares similares
-
Correction for Boullé et al., Elliptic PDE learning is provably data-efficient
Publicado: (2023) -
Geometric Properties for Parabolic and Elliptic PDE's
por: Magnanini, Rolando, et al.
Publicado: (2013) -
Provability, complexity, grammars
por: Beklemishev, Lev, et al.
Publicado: (1999) -
Provable Boolean interaction recovery from tree ensemble obtained via random forests
por: Behr, Merle, et al.
Publicado: (2022) -
Provably correct systems
por: Hinchey, Mike, et al.
Publicado: (2017)