Date: Tuesday 7 May 2024 – 15:00 (Europe/London)
Speaker: Fabian Ruehle, Assistant Professor at the Physics and Mathematics Department of Northeastern University College of Science
Abstract
Despite their successes, machine learning techniques are often stochastic, error-prone, and blackbox. How could they then be used in fields such as theoretical physics and pure mathematics for which error-free results and deep understanding are a must?
I will discuss how we can "gamify" science problems and then tackle them with Reinforcement Learning. This technique can be applied to many hard problems from discrete mathematics and can produce provably correct results for decision problems. Moreover, studying how the game is won, i.e., how problem is solved, is typically easier than trying to interpret a neural network directly. I will illustrate this idea using examples from theoretical physics and mathematics.
This seminar is now available on YouTube https://youtu.be/iCel1TTqjCU
Biography
Dr Ruehle is a Professor at Northeastern University and a Senior Investigator of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions. His research interests lie at the intersection of Mathematics, Theoretical Physics (more precisely string theory), and Machine Learning. He received a Bachelor degree in Physics and Computer Science from the University of Heidelberg and his PhD in Physics from the University of Bonn. Before starting at Northeastern, Dr. Ruehle worked as a postdoctoral researcher at CERN in Geneva, at the University of Oxford, and at DESY in Hamburg.
