A post-doctoral position on Modeling, Optimization, and Transfer for Physics-based Machine Learning is open at the University of Saint-Etienne, France. Depending on the candidate’s profile and interests, different research directions may be envisaged to foster the development of new joint methodological contributions at the interface between machine learning and physics, e.g.: Design of new differentiable and frugal neural network-based architectures, possibly multi-tasks; Develop fast and efficient novel optimization techniques to jointly unveil the underlying physics and learn the numerical solution, bilevel optimization approaches are a possible promising direction; Design new transfer learning methods able to take into account physics-based knowledge.
Candidate profile:
• Ph.D. in computer science, machine learning, applied mathematics, or related. Outstanding applications from physicists will also be considered,
• Good Python/PyTorch programming skills,
• Good knowledge of neural networks and optimization,
• Basic knowledge of partial differential equations is welcome,
• High proficiency in English.
Application Candidate must send the following documents to jordan.frecon.deloire@univ-st- etienne.fr and [email protected] as soon as possible:
• Cover letter with the justification of your skills for the topic,
• A complete Curriculum Vitae,
• Top 3 publications,
• Ph.D. diploma and thesis,
• Any additional document: letter(s) of recommendation, publications, etc.
