Search Results for author: Mathieu Serrurier

Found 11 papers, 2 papers with code

When adversarial attacks become interpretable counterfactual explanations

no code implementations14 Jun 2022 Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin

We argue that, when learning a 1-Lipschitz neural network with the dual loss of an optimal transportation problem, the gradient of the model is both the direction of the transportation plan and the direction to the closest adversarial attack.

Adversarial Attack Counterfactual Explanation

Precipitaion Nowcasting using Deep Neural Network

no code implementations24 Mar 2022 Mohamed Chafik Bakkay, Mathieu Serrurier, Valentin Kivachuk Burda, Florian Dupuy, Naty Citlali Cabrera-Gutierrez, Michael Zamo, Maud-Alix Mader, Olivier Mestre, Guillaume Oller, Jean-Christophe Jouhaud, Laurent Terray

Precipitation nowcasting is of great importance for weather forecast users, for activities ranging from outdoor activities and sports competitions to airport traffic management.

Management

A Hölderian backtracking method for min-max and min-min problems

no code implementations17 Jul 2020 Jérôme Bolte, Lilian Glaudin, Edouard Pauwels, Mathieu Serrurier

We present a new algorithm to solve min-max or min-min problems out of the convex world.

Learning Disentangled Representations of Satellite Image Time Series

no code implementations21 Mar 2019 Eduardo Sanchez, Mathieu Serrurier, Mathias Ortner

In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data.

Change Detection Image Classification +6

Predictive Interval Models for Non-parametric Regression

no code implementations24 Feb 2014 Mohammad Ghasemi Hamed, Mathieu Serrurier, Nicolas Durand

This work presents a new method to find two-sided predictive intervals for non-parametric least squares regression without the homoscedasticity assumption.

Cannot find the paper you are looking for? You can Submit a new open access paper.