186 citations
- Centre BorelliFR8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
- École Nationale Supérieure d’Informatique pour l’Industrie et l’EntrepriseFR5 papers
- École Normale Supérieure Paris-SaclayFR3 papers
- Altair Engineering (France)FR2 papers
- Biomécanique et BioingénierieFR2 papers
- École Normale Supérieure - PSLFR2 papers
- ESPCI ParisFR2 papers
- Laboratoire de Biologie et Pharmacologie AppliquéeFR2 papers
- Laboratoire de Mécanique, Modélisation & Procédés PropresFR2 papers
- Laboratoire Interdisciplinaire de PhysiqueFR2 papers
- Lyon 1 UniversitéFR2 papers
8 papers · 1 filter
Deep Generative Methods and Tire Architecture Design
Fouad Oubari, Raphael Meunier, Rodrigue Décatoire +1
As deep generative models proliferate across the AI landscape, industrial practitioners still face critical yet unanswered questions about which deep generative models best suit co…
Multi-Component VAE with Gaussian Markov Random Field
Fouad Oubari, Mohamed El-Baha, Raphael Meunier +2
Multi-component datasets with intricate dependencies, like industrial assemblies or multi-modal imaging, challenge current generative modeling techniques. Existing Multi-component…
Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
Antoine de Mathelin, François Deheeger, Mathilde Mougeot +1
This paper deals with uncertainty quantification and out-of-distribution detection in deep learning using Bayesian and ensemble methods. It proposes a practical solution to the lac…
Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification
Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot +1
We consider the problem of uncertainty quantification in high dimensional regression and classification for which deep ensemble have proven to be promising methods. Recent observat…
Fixed-budget online adaptive learning for physics-informed neural networks. Towards parameterized problem inference
Thi Nguyen Khoa Nguyen, Thibault Dairay, Raphaël Meunier +2
Physics-Informed Neural Networks (PINNs) have gained much attention in various fields of engineering thanks to their capability of incorporating physical laws into the models. PINN…
Fast and Accurate Importance Weighting for Correcting Sample Bias
Antoine de Mathelin, Francois Deheeger, Mathilde Mougeot +1
Bias in datasets can be very detrimental for appropriate statistical estimation. In response to this problem, importance weighting methods have been developed to match any biased d…