Speaker: Claudio Kopper, Michigan State University/Friedrich-Alexander-Universität Erlangen-Nürnberg
Abstract: In this talk, I will be discussing the fascinating world of machine learning (ML) and its applications to the IceCube neutrino telescope. The field of machine learning has become increasingly important over the last years and now constitutes a vital contribution to the physics output of experiments such as IceCube. I will present recent IceCube results that were made possible by machine learning techniques and highlight the challenges we face when applying ML to IceCube data.
The key challenges to be solved in IceCube are background suppression, particle identification, and event reconstruction, all of which can benefit from the implementation of ML techniques. I will be showcasing the ways in which ML can help with these challenges, and how it has been widely adopted within IceCube, not only to tackle these issues but also in the development of analysis methodology. Overall, the talk will provide an overview of ML techniques, how they are applied in IceCube, and the exciting recent results based on ML.