Grenoble Artificial Intelligence for Physical Sciences Workshop” (GAP2024) in Grenoble

Registration is free but mandatory and can be done here until 15-May.

 

The workshop will explore the intersections between machine learning research and the study of physical systems described by systems of differential equations.

We expect to gather researchers from machine learning and computational physics and diverse application fields, in order to foster collaborations and strengthen connections within the scientific community, and in particular across the alpine arc.

We will feature distinguished keynote speakers who will deliver in-depth lectures on the fundamental concepts and techniques employed in various research domains where machine learning and physical sciences converge. We will have the pleasure to listen to:

 

• Chris Rackauckas – MIT (Scientific machine learning, Julia)
• David Greenberg – Helmoltz Zentrum Hereon (Model-driven machine learning)
• Emmanuel de Bézenac – ETH (Physics-informed neural networks)
• Gilles Louppe – Université of Liège (Simulation-based inference) 
• Nicolas Boullé – University of Cambridge (Operator learning for PDEs)
• Nicolas Brodu – Inria (Continuous causal states)
• Julia Gusak – Inria (Neural ODEs, neural operators, and their efficiency)
• Marc Bocquet – Ecole des Ponts ParisTech (Data assimilation and ML)
• Marylou Gabrié – École Polytechnique (Generative modelling)
• Ronan Fablet – IMT Atlantique (Bi-level optimization for inverse problems)

There will also be a poster session during which researchers will have the opportunity to present their cutting-edge work, demonstrating how they are applying machine learning techniques to address real-world challenges in their respective fields.