Physics-informed learning: using neural networks to solve differential equations
Date and time: 22 April, 12:00 – 13:00 CEST (UTC +2)
Speaker: Matthieu Barreau, Research Fellow within the division of Decision and Control Systems at KTH
Title: Physics-informed learning: using neural networks to solve differential equations
Meeting ID: 695 6088 7455
Watch the recorded presentation:
Abstract: During the last decade, advances in machine learning has yielded many new results in various scientific fields such as image recognition, cognitive science, genomics… The incorporation of physics constraints modelled by differential equations has led to a new paradigm in computational mathematics to approximate solutions to complex and high dimensional problems.
We present physics-informed learning from the basics to the open challenges and its application to traffic flow estimation in this talk.
Bio: Matthieu Barreau got his Master Degree from ISAE-ENSICA (Toulouse, France) and KTH in 2015. In 2019, he received his PhD degree from Université Paul Sabatier (Toulouse, France) on the stability analysis of coupled ordinary and partial differential equations.
For his work, he received the best French PhD thesis award in 2020. He is currently a research fellow within the division of Decision and Control Systems at KTH with Prof. Karl Henrik Johansson on observation of traffic flow using probe vehicles.