Autre Publication Année : 2019

A Taylor Based Sampling Scheme for Machine Learning in Computational Physics

Résumé

Machine Learning (ML) is increasingly used to construct surrogate models for physical simulations. We take advantage of the ability to generate data using numerical simulations programs to train ML models better and achieve accuracy gain with no performance cost. We elaborate a new data sampling scheme based on Taylor approximation to reduce the error of a Deep Neural Network (DNN) when learning the solution of an ordinary differential equations (ODE) system.

Fichier principal
Vignette du fichier
NeurIPS_2019__final.pdf (530.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03114984 , version 1 (20-01-2021)
hal-03114984 , version 2 (28-01-2021)

Licence

Identifiants

  • HAL Id : hal-03114984 , version 1

Citer

Paul Novello, Gaël Poëtte, David Lugato, Pietro Marco Congedo. A Taylor Based Sampling Scheme for Machine Learning in Computational Physics. 2019. ⟨hal-03114984v1⟩
265 Consultations
273 Téléchargements

Partager

  • More