Heidelberg 2022 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
T: Fachverband Teilchenphysik
T 26: Data Analysis, Information Technology and Artificial Intelligence
T 26.6: Vortrag
Montag, 21. März 2022, 17:30–17:45, T-H39
Exploration of neural network architectures for Flavour Tagging algorithms at the LHCb experiment — •Vukan Jevtic1, Quentin Führing1, Christoph Hasse3, Niklas Nolte2, and Claire Prouvé1 — 1Experimentelle Physik 5, TU Dortmund — 2MIT — 3CERN
The LHCb detector at the LHC is specialised for measurements of B meson decays, which open a window into the nature of weak interactions through measurements of rare decays and charge parity (CP) violation. In the Standard Model, CP violation is enabled through a complex phase of the Cabibbo-Kobayashi-Maskawa quark-mixing matrix. B meson mixing refers to the property of neutral B mesons to oscillate between two states of matter, Bq0 and B0q, with different quark contents (i.e. different flavours).
The reconstruction of the flavour at the time of the B meson production is a difficult but indispensable component of measurements of time-dependent CP violation at LHCb. In this talk new approaches to Flavour Tagging via full-event-interpretation techniques will be presented by the example of recurrent neural networks and deep sets.