"Machine Learning: Where to Apply
in Theoretical Physics"
by Jim Halverson (Northeastern University, Boston)
Recent Results at the Intersection of Machine Learning and Theoretical Physics
Abstract: In this talk I will provide a birds-eye-view of some results in machine learning and theoretical physics from the last year, including their motivation and techniques. Topics discussed will include machine learning for Calabi-Yau metrics, knot theory, lattice-QCD, and a correspondence between QFT and neural networks.
June 8, 2021 - 3 - 5 pm
Bethe Center for Theoretical Physics, Bonn