This session was jointly organised by ENBIS and the
Reliability and Uncertainty group of the SFdS,
as part of the Journées de Statistique 2024.
The session focused on industrial applications of deep learning, with particular attention to the interplay between physical modelling, statistical methods, and machine learning.
The session was moderated by Yannig Goude.
Nathan Doumèche
Laboratory of Probability, Statistics and Modelling – EDF Lab
This talk addressed the integration of physical knowledge into machine learning models, with applications to forecasting in industrial contexts.
Loïc Coquelin
French National Metrology and Testing Laboratory (LNE)
This presentation introduced a deep learning approach for estimating particle size distributions from scanning electron microscopy images, highlighting key challenges in industrial metrology.
Eiji Kawasaki
Université Paris-Saclay, CEA, LIST – Palaiseau, France
This talk focused on data subsampling strategies in Bayesian neural networks, discussing trade-offs between computational cost and inference quality.
Detailed information about this session is available on the
Journées de Statistique 2024 website – Joint ENBIS / Reliability & Uncertainty session.