Cargando…
Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
[Image: see text] Reconstructing force fields (FFs) from atomistic simulation data is a challenge since accurate data can be highly expensive. Here, machine learning (ML) models can help to be data economic as they can be successfully constrained using the underlying symmetry and conservation laws o...
Autores principales: | Schmitz, Niklas Frederik, Müller, Klaus-Robert, Chmiela, Stefan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2022
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9639201/ https://www.ncbi.nlm.nih.gov/pubmed/36279418 http://dx.doi.org/10.1021/acs.jpclett.2c02632 |
Ejemplares similares
-
Reconstructing
Kernel-Based Machine Learning Force
Fields with Superlinear Convergence
por: Blücher, Stefan, et al.
Publicado: (2023) -
Machine Learning Force Fields
por: Unke, Oliver T., et al.
Publicado: (2021) -
Towards exact molecular dynamics simulations with machine-learned force fields
por: Chmiela, Stefan, et al.
Publicado: (2018) -
Machine learning of accurate energy-conserving molecular force fields
por: Chmiela, Stefan, et al.
Publicado: (2017) -
Accurate global machine learning force fields for molecules with hundreds of atoms
por: Chmiela, Stefan, et al.
Publicado: (2023)