no code implementations • 18 Mar 2024 • Paul Novello, Joseba Dalmau, Léo Andeol
Based on the work of (Bates et al., 2022), we define new conformal AUROC and conformal FRP@TPR95 metrics, which are corrections that provide probabilistic conservativeness guarantees on the variability of these metrics.
no code implementations • 22 Dec 2023 • Mostafa ElAraby, Sabyasachi Sahoo, Yann Pequignot, Paul Novello, Liam Paull
To build this space, GROOD relies on class prototypes together with a prototype that specifically captures OOD characteristics.
1 code implementation • 11 Jun 2023 • Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Laurent Gardes, Thomas Serre
However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks.
1 code implementation • 26 Jan 2023 • Louis Bethune, Paul Novello, Thibaut Boissin, Guillaume Coiffier, Mathieu Serrurier, Quentin Vincenot, Andres Troya-Galvis
The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against $l2$ adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms.
no code implementations • 27 Sep 2022 • Paul Novello, Gaël Poëtte, David Lugato, Simon Peluchon, Pietro Marco Congedo
To tackle this trade-off, we design a hybrid simulation code coupling a traditional fluid dynamic solver with a neural network approximating the chemical reactions.
1 code implementation • 13 Jul 2022 • Paul Novello, Gaël Poëtte, David Lugato, Pietro Marco Congedo
In this work, we study the use of goal-oriented sensitivity analysis, based on the Hilbert-Schmidt Independence Criterion (HSIC), for hyperparameter analysis and optimization.
1 code implementation • 13 Jun 2022 • Paul Novello, Thomas Fel, David Vigouroux
HSIC measures the dependence between regions of an input image and the output of a model based on kernel embeddings of distributions.
no code implementations • 20 Jan 2021 • Paul Novello, Gaël Poëtte, David Lugato, Pietro Congedo
Machine Learning (ML) is increasingly used to construct surrogate models for physical simulations.
no code implementations • 19 Jan 2021 • Paul Novello, Gaël Poëtte, David Lugato, Pietro Congedo
In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is steep.
no code implementations • 1 Jan 2021 • Paul Novello, Gaël Poëtte, David Lugato, Pietro Congedo
In the context of supervised learning of a function by a Neural Network (NN), we claim and empirically justify that a NN yields better results when the distribution of the data set focuses on regions where the function to learn is steeper.