Collision Course: Particle Physics Meets Machine Learning

Modern machine learning has had an outsized impact on many scientific fields, and particle physics is no exception. What is special about particle physics, though, is the vast amount of theoretical knowledge we already have about many problems in the field and the daunting deluge of data coming from flagship experiments like the Large Hadron Collider.

In this Presidential Lecture, Jesse Thaler will explain how one can teach a machine to “think like a physicist” by embedding theoretical principles into advanced machine learning architectures. At the same time, Thaler will advocate that physicists must learn how to “think like a machine” by capitalizing on advances in computational optimization to perform precision calculations and identify potential signals of new physics.

Thaler is a theoretical particle physicist who fuses techniques from quantum field theory and machine learning to address outstanding questions in fundamental physics. His current research is focused on maximizing the discovery potential of the Large Hadron Collider through new theoretical frameworks and novel data analysis techniques. Thaler joined the MIT Physics Department in 2010 and is currently a professor at the university’s Center for Theoretical Physics. In 2020, he became the inaugural director of the NSF Institute for Artificial Intelligence and Fundamental Interactions.