Abstract:
Physics-Informed Neural Networks (PINNs) are a powerful class of deep learning models that can effectively learn complex physical phenomena by integrating data with known physical equations and constraints. PINNs have gained significant popularity in recent years, primarily due to their ability to rapidly and accurately model the behavior of complex systems, even when working with incomplete or noisy data. By leveraging both data-driven and physics-based approaches, PINNs offer a unique advantage over traditional machine learning models and have shown great potential in various fields, including physics, engineering, and finance. In this seminar, I will introduce the concept of PINNs and provide a theoretical basis for understanding how they work. I will discuss key challenges in developing PINNs, and explore current research trends in PINNs, including multi-fidelity modeling and transfer learning. This seminar is tailored for researchers who are interested in using PINNs but have no prior experience with them.
Dr. Mohammad Mahdi Rajabi is a post-doctoral researcher within the Faculty of Science, Technology and Medicine at the University of Luxembourg.
The Machine Learning Seminar is a regular weekly seminar series aiming to harbour presentations of fundamental and methodological advances in data science and machine learning as well as to discuss application areas presented by domain specialists. The uniqueness of the seminar series lies in its attempt to extract common denominators between domain areas and to challenge existing methodologies. The focus is thus on theory and applications to a wide range of domains, including Computational Physics and Engineering, Computational Biology and Life Sciences, Computational Behavioural and Social Sciences. More information about the ML Seminar, together with video recordings from past meetings you will find here: https://legato-team.eu/seminars/