518 citations
- Centre National de la Recherche ScientifiqueFR204 papers
- Université Toulouse III - Paul SabatierFR140 papers
- Institut de Recherche en Informatique de ToulouseFR139 papers
- Université Toulouse-I-CapitoleFR139 papers
- Université Toulouse - Jean JaurèsFR139 papers
- Université de BordeauxFR122 papers
- Institut de Mathématiques de MarseilleFR120 papers
- Château GombertFR83 papers
- Laboratoire Bordelais de Recherche en InformatiqueFR73 papers
- Aix-Marseille UniversitéFR42 papers
- Centrale MéditerranéeFR39 papers
- Institut de Mécanique et d'Ingénierie de BordeauxFR36 papers
12 papers · 1 filter
Two-level deep domain decomposition method
Victorita Dolean, Serge Gratton, Alexander Heinlein +1
This study presents a two-level Deep Domain Decomposition Method (Deep-DDM) augmented with a coarse-level network for solving boundary value problems using physics-informed neural…
DECWA : Density-Based Clustering using Wasserstein Distance
Nabil El Malki, Robin Cugny, Olivier Teste +1
Clustering is a data analysis method for extracting knowledge by discovering groups of data called clusters. Among these methods, state-of-the-art density-based clustering methods…
Decentralized Smart Charging of Large-Scale EVs using Adaptive Multi-Agent Multi-Armed Bandits
Sharyal Zafar, Raphaël Feraud, Anne Blavette +2
The drastic growth of electric vehicles and photovoltaics can introduce new challenges, such as electrical current congestion and voltage limit violations due to peak load demands.…
L'explicabilité au service de l'extraction de connaissances : application à des données médicales
Robin Cugny, Emmanuel Doumard, Elodie Escriva +1
The use of machine learning has increased dramatically in the last decade. The lack of transparency is now a limiting factor, which the field of explainability wants to address. Fu…
The Inadequacy of Shapley Values for Explainability
Xuanxiang Huang, Joao Marques-Silva
This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importan…
Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions
Robin Cugny, Julien Aligon, Max Chevalier +2
In recent years, a large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed to explain existing ML (Machine Learning) models or to create interpretabl…