Data publication: Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks

Autor:	Maddu, S., Sturm, D., Müller, C. L., Sbalzarini, I. F.
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	data-driven modeling multi-objective optimization sobolev training catastrophic forgetting computational physics deep learning physics informed neural networks active turbulence
Zdroj:	Publication year 2021Programming language: PythonSystem requirements: python, numpy, scipy, sklearn, torch, matplotlib, seaborn, pandasLicense: MITHosted on GitHub: Link to location
Popis:	Scripts and notebooks to reproduce the results presented in the paper "Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks", Maddu et al., 2021
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=od______4577::84a46dd93af3819e2889c616ef21d861 https://www.hzdr.de/publications/Publ-33337-1 Zobrazit plný text záznamu