Learning physics models that generalize (Tobias Pfaff)

June 22, 2022, 4:00 p.m. (CEST)

SimTech Colloquium

Time: June 22, 2022, 4:00 p.m. (CEST)
Download as iCal:

Place: https://unistuttgart.webex.com/unistuttgart/j.php?MTID=m1f20ca8706d56cf9c2c0b9494a8eca81

While there's growing interest in using machine learning to speed up numerical simulations, many existing methods are only accurate in a very narrow range around the training data. In practice, this often means running large numbers of expensive reference simulations to generate targeted training data for each problem, negating performance benefits of using learned methods. But it doesn't have to be that way. In this talk, we'll explore how to construct GNN-based models which learn reusable knowledge and generalize well; and we'll see how exploiting a set of very general inductive biases allows us to accurately predict dynamics of significantly bigger and more complex systems than seen in training. I will show some demonstrations on a range of physical systems, from aerodynamics over structural mechanics to cloth, and discuss what we can do with these models beyond forward prediction.

Tobias Pfaff is a senior research scientist at DeepMind, working on RL and structured models, in particular GNN physics models. His background is in physics simulation; in his PhD (ETH Zurich) and postdoc (UC Berkeley), he studied turbulent fluids, fracture and cloth simulation for computer graphics, and co-authored the simulation frameworks Mantaflow (the default fluid solver in Blender) and ArcSim.

July 2022

June 2022

May 2022

April 2022

March 2022

February 2022

January 2022

December 2021

November 2021

October 2021

September 2021

July 2021

June 2021

May 2021

April 2021

March 2021

February 2021

January 2021

December 2020

November 2020

October 2020

August 2020

July 2020

June 2020

May 2020

March 2020

February 2020

January 2020

December 2019

November 2019

October 2019

September 2019

July 2019

June 2019

May 2019

June 2019

November 2019

To the top of the page