Combining Maximum-Likelihood with Deep Learning for Event Reconstruction in IceCube

  • 152 views

  • 0 favorites

  • uploaded July 5, 2021

Discussion timeslot (ZOOM-Meeting): 15. July 2021 - 18:00
ZOOM-Meeting URL: https://desy.zoom.us/j/91999581729
ZOOM-Meeting ID: 91999581729
ZOOM-Meeting Passcode: ICRC2021
Corresponding Session: https://icrc2021-venue.desy.de/channel/37-Reconstruction-amp-Analysis-Techniques-NU/126
Live-Stream URL: https://icrc2021-venue.desy.de/livestream/Discussion-05/6

Abstract:
'The field of deep learning has become increasingly important for particle physics experiments, yielding a multitude of advances, predominantly in event classification and reconstruction tasks. Many of these applications have been adopted from other domains. However, data in the field of physics are unique in the context of machine learning, insofar as their generation process and the law and symmetries they abide by are usually well understood. Most commonly used deep learning architectures fail at utilizing this available information. In contrast, more traditional likelihood-based methods are capable of exploiting domain knowledge, but they are often limited by computational complexity. In this contribution, a hybrid approach is presented that utilizes generative neural networks to approximate the likelihood, which may then be used in a traditional maximum-likelihood setting. Domain knowledge, such as invariances and detector characteristics, can easily be incorporated in this approach. The hybrid approach is illustrated by the example of event reconstruction in IceCube.'

Authors: Mirco Hünnefeld | For the IceCube Collaboration
Collaboration: IceCube

Indico-ID: 745
Proceeding URL: https://pos.sissa.it/395/1065

Tags:
Presenter:

Mirco Hünnefeld


Additional files

More Media in "Neutrino"