Recent innovations in mathematics, computer science, and engineering have enabled more and more sophisticated numerical simulations. However, some simulations remain computationally unaffordable, even for the most powerful supercomputers. Lately, machine learning has proven its ability to improve the state-of-the-art in many fields, notoriously computer vision, language understanding, or robotics. This thesis settles in the high-stakes emerging field of Scientific Machine Learning which studies the application of machine learning to scientific computing. More specifically, we consider the use of deep learning to accelerate numerical simulations.We focus on approximating some components of Partial Differential Equation (PDE) based simulation...
La modélisation numérique de la turbulence est une des approches classiques pour étudier la complexi...
La modélisation de phénomènes complexes rencontrés dans les problématiques industrielles peut condui...
Les algorithmes d’apprentissage automatique utilisant des réseaux de neurones profonds ont récemment...
Recent innovations in mathematics, computer science, and engineering have enabled more and more soph...
Numerical modeling of Turbulence is one of the classical approaches for studying active scales dynam...
Many engineering applications require accurate numerical simulations of non-linear structures in rea...
Partial differential equations (PDEs) are an essential modeling tool for the numerical simulation of...
Neural network models became highly popular during the last decade due to their efficiency in variou...
Deep learning algorithms allow computers to perform cognitive tasks ranging from vision to natural l...
This thesis consists of three scientific publications that use machine learning methods to understan...
Because computer performance is always increasing, the numerical simulations of physical phenomena b...
Recent developments in deep learning have pushed the limits of possibilities with large language mod...
Computer vision is a strategic field, in consequence of its great number of potential applications w...
International audienceThe use of modeling and simulation now allows considerable performance for met...
Artificial intelligence is a field that, historically, has benefited from the combination of ideas f...
La modélisation numérique de la turbulence est une des approches classiques pour étudier la complexi...
La modélisation de phénomènes complexes rencontrés dans les problématiques industrielles peut condui...
Les algorithmes d’apprentissage automatique utilisant des réseaux de neurones profonds ont récemment...
Recent innovations in mathematics, computer science, and engineering have enabled more and more soph...
Numerical modeling of Turbulence is one of the classical approaches for studying active scales dynam...
Many engineering applications require accurate numerical simulations of non-linear structures in rea...
Partial differential equations (PDEs) are an essential modeling tool for the numerical simulation of...
Neural network models became highly popular during the last decade due to their efficiency in variou...
Deep learning algorithms allow computers to perform cognitive tasks ranging from vision to natural l...
This thesis consists of three scientific publications that use machine learning methods to understan...
Because computer performance is always increasing, the numerical simulations of physical phenomena b...
Recent developments in deep learning have pushed the limits of possibilities with large language mod...
Computer vision is a strategic field, in consequence of its great number of potential applications w...
International audienceThe use of modeling and simulation now allows considerable performance for met...
Artificial intelligence is a field that, historically, has benefited from the combination of ideas f...
La modélisation numérique de la turbulence est une des approches classiques pour étudier la complexi...
La modélisation de phénomènes complexes rencontrés dans les problématiques industrielles peut condui...
Les algorithmes d’apprentissage automatique utilisant des réseaux de neurones profonds ont récemment...