Presenter: Sven Krippendorf, LMU
Title: Machine Learning & String Theory
Abstract: Machine Learning techniques allow new insights in various areas of science, and string theory is no exception to this. To showcase the use of ML in string theory, I will give a brief overview on two activities: 1) learning the metric of the compact extra-dimensional space, and 2) the sampling of flux vacua with particular low-energy properties to identify universal features of such solutions.
I will comment on two technical aspects which are of interest outside of their application: For our metric learning we heavily rely on incorporating appropriate domain knowledge into our networks for identifying efficient neural networks. Our sampling of the discrete solution space is done with reinforcement learning and genetic algorithms.
As usual, the format will be a short presentation followed by plenty of discussion.
Please let all interested know about the Journal Club (get them to send their Email address). We are looking forward to lively discussions.