Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Bucci, Michele Alessandro"'
Autor:
Nastorg, Matthieu, Gratien, Jean-Marc, Faney, Thibault, Bucci, Michele Alessandro, Charpiat, Guillaume, Schoenauer, Marc
Large-scale numerical simulations often come at the expense of daunting computations. High-Performance Computing has enhanced the process, but adapting legacy codes to leverage parallel GPU computations remains challenging. Meanwhile, Machine Learnin
Externí odkaz:
http://arxiv.org/abs/2402.08296
The spread of machine learning (ML) techniques in combination with the availability of high-quality experimental and numerical data boosted in recent years numerous applications in fluid mechanics. Among those, examples of closure models for turbulen
Externí odkaz:
http://arxiv.org/abs/2303.03806
Autor:
Nastorg, Matthieu, Bucci, Michele Alessandro, Faney, Thibault, Gratien, Jean-Marc, Charpiat, Guillaume, Schoenauer, Marc
This paper presents $\Psi$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions. By leveraging the Implicit Layer Theory, $\Psi$-GNN models an "infinitely" deep network, thus
Externí odkaz:
http://arxiv.org/abs/2302.10891
Autor:
Menier, Emmanuel, Bucci, Michele Alessandro, Yagoubi, Mouadh, Mathelin, Lionel, Dairay, Thibault, Meunier, Raphael, Schoenauer, Marc
Reduced order modeling methods are often used as a mean to reduce simulation costs in industrial applications. Despite their computational advantages, reduced order models (ROMs) often fail to accurately reproduce complex dynamics encountered in real
Externí odkaz:
http://arxiv.org/abs/2211.16999
Autor:
Nastorg, Matthieu, Schoenauer, Marc, Charpiat, Guillaume, Faney, Thibault, Gratien, Jean-Marc, Bucci, Michele-Alessandro
Publikováno v:
Machine Learning and the Physical Sciences workshop, NeurIPS 2022, Dec 2022, New-Orleans, United States
This paper proposes a novel Machine Learning-based approach to solve a Poisson problem with mixed boundary conditions. Leveraging Graph Neural Networks, we develop a model able to process unstructured grids with the advantage of enforcing boundary co
Externí odkaz:
http://arxiv.org/abs/2211.11763
Autor:
Menier, Emmanuel, Bucci, Michele Alessandro, Yagoubi, Mouadh, Mathelin, Lionel, Schoenauer, Marc
This paper proposes a novel approach to domain translation. Leveraging established parallels between generative models and dynamical systems, we propose a reformulation of the Cycle-GAN architecture. By embedding our model with a Hamiltonian structur
Externí odkaz:
http://arxiv.org/abs/2207.03843
Autor:
Nastorg, Matthieu, Bucci, Michele-Alessandro, Faney, Thibault, Gratien, Jean-Marc, Charpiat, Guillaume, Schoenauer, Marc
Publikováno v:
In Computers and Mathematics with Applications 15 December 2024 176:270-288
Autor:
Menier, Emmanuel, Bucci, Michele Alessandro, Yagoubi, Mouadh, Mathelin, Lionel, Schoenauer, Marc
Publikováno v:
Computer Methods in Applied Mechanics and Engineering, Volume 410, 15 May 2023, 115985
Model order reduction through the POD-Galerkin method can lead to dramatic gains in terms of computational efficiency in solving physical problems. However, the applicability of the method to non linear high-dimensional dynamical systems such as the
Externí odkaz:
http://arxiv.org/abs/2202.10746
Autor:
Bucci, Michele Alessandro, Semeraro, Onofrio, Allauzen, Alexandre, Wisniewski, Guillaume, Cordier, Laurent, Mathelin, Lionel
Deep Reinforcement Learning (DRL) is applied to control a nonlinear, chaotic system governed by the one-dimensional Kuramoto-Sivashinsky (KS) equation. DRL uses reinforcement learning principles for the determination of optimal control solutions and
Externí odkaz:
http://arxiv.org/abs/1906.07672
Autor:
Bucci, Michele Alessandro
Cette thèse vise à mettre en évidence les limites du contrôle passif en utilisant des éléments de rugosité miniaturisés. La topologie des écoulements induite par la présence d’une rugosité cylindrique et des générateurs de tourbillons
Externí odkaz:
http://www.theses.fr/2017ENAM0053/document