The duality between particle methods and artificial neural networks

Abstract The algorithm behind particle methods is extremely versatile and used in a variety of applications that range from molecular dynamics to astrophysics. For continuum mechanics applications, the concept of ‘particle’ can be generalized to include discrete portions of solid and liquid matter....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: A. Alexiadis, M. J. H. Simmons, K. Stamatopoulos, H. K. Batchelor, I. Moulitsas
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ca0984051e2b46a9a399d40d1812f73e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ca0984051e2b46a9a399d40d1812f73e
record_format dspace
spelling oai:doaj.org-article:ca0984051e2b46a9a399d40d1812f73e2021-12-02T18:51:28ZThe duality between particle methods and artificial neural networks10.1038/s41598-020-73329-02045-2322https://doaj.org/article/ca0984051e2b46a9a399d40d1812f73e2020-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-73329-0https://doaj.org/toc/2045-2322Abstract The algorithm behind particle methods is extremely versatile and used in a variety of applications that range from molecular dynamics to astrophysics. For continuum mechanics applications, the concept of ‘particle’ can be generalized to include discrete portions of solid and liquid matter. This study shows that it is possible to further extend the concept of ‘particle’ to include artificial neurons used in Artificial Intelligence. This produces a new class of computational methods based on ‘particle-neuron duals’ that combines the ability of computational particles to model physical systems and the ability of artificial neurons to learn from data. The method is validated with a multiphysics model of the intestine that autonomously learns how to coordinate its contractions to propel the luminal content forward (peristalsis). Training is achieved with Deep Reinforcement Learning. The particle-neuron duality has the advantage of extending particle methods to systems where the underlying physics is only partially known, but we have observations that allow us to empirically describe the missing features in terms of reward function. During the simulation, the model evolves autonomously adapting its response to the available observations, while remaining consistent with the known physics of the system.A. AlexiadisM. J. H. SimmonsK. StamatopoulosH. K. BatchelorI. MoulitsasNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-7 (2020)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
A. Alexiadis
M. J. H. Simmons
K. Stamatopoulos
H. K. Batchelor
I. Moulitsas
The duality between particle methods and artificial neural networks
description Abstract The algorithm behind particle methods is extremely versatile and used in a variety of applications that range from molecular dynamics to astrophysics. For continuum mechanics applications, the concept of ‘particle’ can be generalized to include discrete portions of solid and liquid matter. This study shows that it is possible to further extend the concept of ‘particle’ to include artificial neurons used in Artificial Intelligence. This produces a new class of computational methods based on ‘particle-neuron duals’ that combines the ability of computational particles to model physical systems and the ability of artificial neurons to learn from data. The method is validated with a multiphysics model of the intestine that autonomously learns how to coordinate its contractions to propel the luminal content forward (peristalsis). Training is achieved with Deep Reinforcement Learning. The particle-neuron duality has the advantage of extending particle methods to systems where the underlying physics is only partially known, but we have observations that allow us to empirically describe the missing features in terms of reward function. During the simulation, the model evolves autonomously adapting its response to the available observations, while remaining consistent with the known physics of the system.
format article
author A. Alexiadis
M. J. H. Simmons
K. Stamatopoulos
H. K. Batchelor
I. Moulitsas
author_facet A. Alexiadis
M. J. H. Simmons
K. Stamatopoulos
H. K. Batchelor
I. Moulitsas
author_sort A. Alexiadis
title The duality between particle methods and artificial neural networks
title_short The duality between particle methods and artificial neural networks
title_full The duality between particle methods and artificial neural networks
title_fullStr The duality between particle methods and artificial neural networks
title_full_unstemmed The duality between particle methods and artificial neural networks
title_sort duality between particle methods and artificial neural networks
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/ca0984051e2b46a9a399d40d1812f73e
work_keys_str_mv AT aalexiadis thedualitybetweenparticlemethodsandartificialneuralnetworks
AT mjhsimmons thedualitybetweenparticlemethodsandartificialneuralnetworks
AT kstamatopoulos thedualitybetweenparticlemethodsandartificialneuralnetworks
AT hkbatchelor thedualitybetweenparticlemethodsandartificialneuralnetworks
AT imoulitsas thedualitybetweenparticlemethodsandartificialneuralnetworks
AT aalexiadis dualitybetweenparticlemethodsandartificialneuralnetworks
AT mjhsimmons dualitybetweenparticlemethodsandartificialneuralnetworks
AT kstamatopoulos dualitybetweenparticlemethodsandartificialneuralnetworks
AT hkbatchelor dualitybetweenparticlemethodsandartificialneuralnetworks
AT imoulitsas dualitybetweenparticlemethodsandartificialneuralnetworks
_version_ 1718377412207575040