Learning Port Hamiltonian Structures Using PINNs Architecture

Explore the intersection of machine learning and dynamical systems in this 30-minute conference talk by Karim Cherifi from TU Berlin. Delve into the application of Physics-Informed Neural Networks (PINNs) architecture for learning Port Hamiltonian structures, a powerful framework for modeling complex physical systems. Gain insights into cutting-edge research presented at the Fourth Symposium on Machine Learning and Dynamical Systems, hosted by the Fields Institute.