Learning Data for Neural-Network-Based Numerical Solution of PDEs: Application to Dirichlet-to-Neumann Problems

We propose neural-network-based algorithms for the numerical solution of boundary-value problems for the Laplace equation. Such a numerical solution is inherently mesh-free, and in the approximation process, stochastic algorithms are employed. The chief challenge in the solution framework is to gene...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Ferenc Izsák, Taki Eddine Djebbar
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	MDPI AG 2023-02-01
Saila:	Algorithms
Gaiak:	boundary-value problems neural networks Dirichlet-to-Neumann problem learning data method of fundamental solutions
Sarrera elektronikoa:	https://www.mdpi.com/1999-4893/16/2/111
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!