Jan 2 – 7, 2018
Skeikampen, Norway
Europe/Oslo timezone

Deep learning particle tracks in the CMS detector

Jan 4, 2018, 6:15 PM
Skeikampen, Norway

Skeikampen, Norway

Hotellvegen 3, 2652 Svingvoll, Norway
Contributed talk Particle Physics and Artificial Intelligence Thursday PM


Joona Juhani Havukainen (Helsinki Institute of Physics (FI))


In order to improve track reconstruction in Run 2 and to prepare for the increasingly difficult detector conditions of Run 3 at the Compact Muon Solenoid (CMS) detector, the use of novel machine learning methods in the CMS tracking are being studied. These methods provide ways to deal with for example the high particle densities, growing combinatorics and track quality assignments in the tracker. In this talk I will discuss the CMS track reconstruction, it's challenges in Run 2 and Run 3 and how we can use machine learning to ensure the continued high level of performance in track reconstruction.

Primary author

Joona Juhani Havukainen (Helsinki Institute of Physics (FI))

Presentation materials