Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting

In machine learning approaches relevant for chemical physics and material science, neural network potentials can be trained on the experimental data. The authors propose a training method applying trajectory reweighting instead of direct backpropagation for improved robustness and reduced computatio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Stephan Thaler, Julija Zavadlav
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/6c34aa6706384e3b9d43a8893868e6f3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6c34aa6706384e3b9d43a8893868e6f3
record_format	dspace
spelling	oai:doaj.org-article:6c34aa6706384e3b9d43a8893868e6f32021-11-28T12:33:07ZLearning neural network potentials from experimental data via Differentiable Trajectory Reweighting10.1038/s41467-021-27241-42041-1723https://doaj.org/article/6c34aa6706384e3b9d43a8893868e6f32021-11-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-27241-4https://doaj.org/toc/2041-1723In machine learning approaches relevant for chemical physics and material science, neural network potentials can be trained on the experimental data. The authors propose a training method applying trajectory reweighting instead of direct backpropagation for improved robustness and reduced computational cost.Stephan ThalerJulija ZavadlavNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Stephan Thaler Julija Zavadlav Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
description	In machine learning approaches relevant for chemical physics and material science, neural network potentials can be trained on the experimental data. The authors propose a training method applying trajectory reweighting instead of direct backpropagation for improved robustness and reduced computational cost.
format	article
author	Stephan Thaler Julija Zavadlav
author_facet	Stephan Thaler Julija Zavadlav
author_sort	Stephan Thaler
title	Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
title_short	Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
title_full	Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
title_fullStr	Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
title_full_unstemmed	Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
title_sort	learning neural network potentials from experimental data via differentiable trajectory reweighting
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6c34aa6706384e3b9d43a8893868e6f3
work_keys_str_mv	AT stephanthaler learningneuralnetworkpotentialsfromexperimentaldataviadifferentiabletrajectoryreweighting AT julijazavadlav learningneuralnetworkpotentialsfromexperimentaldataviadifferentiabletrajectoryreweighting
_version_	1718407894950477824

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting

Ejemplares similares