Archivio Istituzionale della RicercaWe introduce the lowest-order Neural Approximated Virtual Element Method, a novel polygonal method that relies on neural networks to eliminate the need for projection and stabilization operators in the Virtual Element Method. In this paper, we discuss its formulation and detail the strategy for training the underlying neural network. The viability of the new method is tested through numerical experiments on elliptic problems.
The Lowest-Order Neural Approximated Virtual Element Method / Berrone, Stefano; Oberto, Davide; Pintore, Moreno; Teora, Gioana. - 153 - 1:(2025). (Intervento presentato al convegno ENUMATH: European Conference on Numerical Mathematics and Advanced Applications tenutosi a Lisbona (Portogallo) nel Settembre 4-8 2025) [10.1007/978-3-031-86173-4_13].
The Lowest-Order Neural Approximated Virtual Element Method
Berrone, Stefano;Teora, Gioana
2025
Abstract
We introduce the lowest-order Neural Approximated Virtual Element Method, a novel polygonal method that relies on neural networks to eliminate the need for projection and stabilization operators in the Virtual Element Method. In this paper, we discuss its formulation and detail the strategy for training the underlying neural network. The viability of the new method is tested through numerical experiments on elliptic problems.
| File | Dimensione | Formato | |
|---|---|---|---|
|
navem_prooceding_pubblicato.pdf
accesso riservato
Descrizione: Versione editoriale
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
986.83 kB
Formato
Adobe PDF
|
986.83 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
final_main.pdf
embargo fino al 25/04/2026
Descrizione: Accepted Manuscript
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
652.34 kB
Formato
Adobe PDF
|
652.34 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2999718