SMuK 2023 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
T: Fachverband Teilchenphysik
T 10: ML Methods I
T 10.4: Vortrag
Montag, 20. März 2023, 17:15–17:30, HSZ/0405
Particle identification at Belle II using Neural Networks — •xavier simo1,2, daniel greenwald1, stefan wallner2, and stephan paul1,2 — 1Techincal University Munich (TUM) — 2Max Planck Institute for Physics (MPP)
We will present improvements to the charged-particle identification algorithms used by the Belle II experiment located at KEK, Japan. So far, different approaches have been used to tackle the challenge of combining the information from each subdetector into a single variable for particle identification in an optimal way. We will present evaluations of the performance of a Neural Network based approach that combines information such as the likelihood values from each subdetector and the measured momentum of the particle track.
funded by the DFG under Germany’s Excellence Strategy - EXC2094 - 390783311 and BMBF Verbundforschung (05H21WOKBA BELLE2)