This program studies the foundations of machine learning models and their properties, as well as the interactions between data-driven and analytical models in, for example, the efficient simulation of complex physical processes. Topics include robustness, optimization, verification of performance guarantees, proposing a hybrid AI approach for accelerating the simulation of physical models, and designing and validating certifiable architectures of critical autonomous systems (e.g. in aeronautics and automotive sectors)..

The DEEL (DEpendable Explainable Learning) is a collaborative research project of ANITI that aims to develop technological building blocks toward dependable, robust, explainable and certifiable AI critical systems. DEEL is in collaboration with partners from IVADO (The Institute for Data Valorization) and CRIACQ (Consortium for Research and Innovation in Aerospace in Quebec) in Canada

En particulier, ces sujets de recherche sont traités en partie dans le cadre du projet de recherche collaborative DEEL (DEpendable Explainable Learning) associant des partenaires d’ANITI, qui est mené en collaboration avec des partenaires canadiens : IVADO (The Institute for Data Valorization) et CRIACQ (Consortium pour la recherche et l’innovation en aérospatiale au Québec), dans le but de développer des briques technologiques permettant la mise en œuvre de systèmes critiques d’IA fiables, robustes, explicables et certifiables.

Les thèmes associés au programme IA certifiable :

  • Certifiable AI — Safe design and embeddability
  • Explainability
  • Fair Learning
  • Certifiable AI
  • AI & physical models
  • Optimization & games theory for AI
  • Automated reasoning and decision making

> Découvrez tous les thèmes


Coordination


Serge Gratton


Gregory Flandin

en_GBEnglish