148 citations
- Université Paris-SaclayFR12 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- CentraleSupélecFR7 papers
- École PolytechniqueFR4 papers
- Laboratoire d'Informatique de l'École PolytechniqueFR4 papers
- Laboratoire Interdisciplinaire des Sciences du NumériqueFR4 papers
- Mathématiques et Informatique pour la Complexité et les Systèmes4 papers
- Sorbonne UniversitéFR4 papers
- Institut national de recherche en sciences et technologies du numériqueFR3 papers
- Institut Systèmes Intelligents et de RobotiqueFR3 papers
- Office National d'Études et de Recherches AérospatialesFR3 papers
- Safran (France)FR3 papers
59 papers
I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
Lucas Thil, Jesse Read, Rim Kaddah +1
Accurate remaining useful life (RUL) prediction hinges on the quality of health indicators (HIs), yet existing methods often fail to disentangle complex degradation mechanisms in m…
Resource-Efficient Synthesis of Sparse Quantum States
Renaud Vilmart, Sunheang Ty, Chetra Mang
Preparing a quantum circuit that implements a given sparse state is an important building block that is necessary for many different quantum algorithms. In the context of fault-tol…
Feasibility Study of CNNs and MLPs for Radiation Heat Transfer in 2-D Furnaces with Spectrally Participative Gases
Axel TahmasebiMoradi, Vincent Ren, Benjamin Le-Creurer +2
Aiming to reduce the computational cost of numerical simulations, a convolutional neural network (CNN) and a multi-layer perceptron (MLP) are introduced to build a surrogate model…
Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings
Lucas Mattioli, Youness Ait Hadichou, Sabrina Chaouche +1
Training models on uncurated Text Embeddings (TEs) derived from raw tabular data can lead to a severe failure mode known as model collapse, where predictions converge to a single c…
NeurIPS 2024 ML4CFD Competition: Results and Retrospective Analysis
Mouadh Yagoubi, David Danan, Milad Leyli-Abadi +15
The integration of machine learning (ML) into the physical sciences is reshaping computational paradigms, offering the potential to accelerate demanding simulations such as computa…
A new methodology to decompose a parametric domain using reduced order data manifold in machine learning
Chetra Mang, Axel TahmasebiMoradi, Mouadh Yagoubi
We propose a new methodology for parametric domain decomposition using iterative principal component analysis. Starting with iterative principle component analysis, the high dimens…