no code implementations • 27 Sep 2023 • Valentin Lemaire, Youssef Achenchabe, Lucas Ody, Houssem Eddine Souid, Gianmarco Aversano, Nicolas Posocco, Sabri Skhiri
In this paper, we present SANGEA, a sizeable synthetic graph generation framework which extends the applicability of any SGG to large graphs.
1 code implementation • 7 Jul 2022 • Gregory Scafarto, Nicolas Posocco, Antoine Bonnefoy
In this paper we show a first link between uncertainty and explainability, by studying the relation between calibration and interpretation.
1 code implementation • 8 Sep 2021 • Nicolas Posocco, Antoine Bonnefoy
Thus this paper focuses on the empirical evaluation of calibration metrics in the context of classification.
1 code implementation • 30 Jun 2021 • Simon Tihon, Muhammad Usama Javaid, Damien Fourure, Nicolas Posocco, Thomas Peel
Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications.
1 code implementation • 30 Jun 2021 • Damien Fourure, Muhammad Usama Javaid, Nicolas Posocco, Simon Tihon
Moreover, we show that the F1-score and the AVPR cannot be used to compare performances on different datasets as they do not reflect the intrinsic difficulty of modeling such data.
1 code implementation • 4 Nov 2019 • Florian Dubost, Benjamin Collery, Antonin Renaudier, Axel Roc, Nicolas Posocco, Gerda Bortsova, Wiro Niessen, Marleen de Bruijne
For diagnosis and treatment planning of scoliosis, spinal curvature can be estimated using Cobb angles.