Deep Learning Methods in Mathematical Physics
Speaker: Prof. Ovidiu Calin, Department of Mathematics & Statistics, Eastern Michigan University
Host: S Baskar
Title: Deep Learning for Solving Equations
Time, day and date: 11:30:00 AM – 12:30:00 PM, Monday, February 17
Venue: Ramanujan Hall
Abstract: This lecture presents how deep learning can be used to solve a broad class of mathematical equations, including algebraic, functional, integral, and differential equations. We discuss neural-network-based formulations for direct and inverse problems, illustrate solution strategies for ordinary and partial differential equations, and highlight modern techniques such as multiphase resolution and equation discovery. The lecture emphasizes how neural networks provide a unified framework for solving diverse equation types arising in applied mathematics and physics.
The details of the lectures in this series are given in the following PDF document:
https://drive.google.com/file/d/1MyJ-QN_VswUaRcuaztPdG2TgWbvXybhW/view?usp=sharing