Deep Learning Methods in Mathematical Physics
Speaker: Prof. Ovidiu Calin, Department of Mathematics & Statistics, Eastern Michigan University
Host: S Baskar
Title: Lagrangian Systems
Time, day and date: 12:00:00 PM – 1:00:00 PM, Thursday, February 19
Venue: Ramanujan Hall
Abstract: This lecture introduces Lagrangian systems from the perspective of neural-network-based modeling. We study classical variational systems such as the harmonic oscillator, catenary, brachistochrone, simple pendulum, and Euler’s elastica, and show how their dynamics can be learned and reproduced using neural networks. The lecture highlights the connection between variational principles, trajectory optimization, and modern data-driven approaches to classical mechanics.