SMuK 2023 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 9: DAQ NN/ML – HW

T 9.2: Vortrag

Montag, 20. März 2023, 16:45–17:00, HSZ/0301

Machine learning based triggers for VBF H → inv at the Level-1 trigger system of CMS — •Shahin Sepanlou, Johannes Haller, Gregor Kasieczka, Finn Labe, Artur Lobanov, and Matthias Schröder — Institut für Experimentalphysik, Universität Hamburg

At the CMS experiment, a two-level trigger system is used to decide which collision events to store for later analysis. The Level-1 trigger is subject to strict latency, resource and rate constraints. To handle the even more challenging High Luminosity-LHC environment, novel strategies in the trigger system are necessary. Therefore, in this talk studies towards a topological trigger algorithm using fast machine learning on FPGAs are presented. The vector boson fusion production of a Higgs boson decaying to invisible particles is used as an example process that is difficult to select with classical trigger strategies and would benefit from machine learning based approaches.