49 citations
- IRT M2PFR4 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Institut de Mathématiques de ToulouseFR2 papers
- Institut de Recherche en Informatique de ToulouseFR2 papers
- Aix-Marseille UniversitéFR1 paper
- Brown UniversityUS1 paper
- Centre Européen de Recherche et de Formation Avancée en Calcul ScientifiqueFR1 paper
- Dassault Systèmes (France)FR1 paper
- Dassault Systèmes (United States)US1 paper
- École Centrale de LilleFR1 paper
- Florence (Netherlands)NL1 paper
- Laboratoire de Mécanique, Multiphysique, MultiéchelleFR1 paper
Showing 2019Show all
3 papers · 1 filter
physics.flu-dyn2019★ 49 cited
Surrogate Modeling of Aerodynamic Simulations for Multiple Operating Conditions Using Machine Learning
Romain Dupuis, Jean-Christophe Jouhaud, Pierre Sagaut
This article presents an original methodology for the prediction of steady turbulent aerodynamic fields. Due to the important computational cost of high-fidelity aerodynamic simula…
math.OC2019★ 5 cited
Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning
Jérôme Bolte, Edouard Pauwels
Modern problems in AI or in numerical analysis require nonsmooth approaches with a flexible calculus. We introduce generalized derivatives called conservative fields for which we d…
cs.CV2019★ 3 cited
Learning Disentangled Representations of Satellite Image Time Series
Eduardo Sanchez, Mathieu Serrurier, Mathias Ortner
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additio…