Speakers
Karolos Potamianos
(University of Oxford (GB))
Daniel Dobos
(Lancaster University (GB))
Kristiane Novotny
(gluoNNet)
Description
Can quantum machine learning algorithms tackle particle identification challenges, do they provide any kind of new insights ?
In the high pileup conditions at the High-Luminosity LHC, particle identification using vertex detectors in combination with calorimetry becomes a challenging task. The use of detector hit timing information, through high precision (pico-second) time resolved tracking (4D tracking detectors) and fast calorimetry, is a promising possibility to resolve combinatorial ambiguities in the tracking. So is the use of extended classical and Quantum Machine Learning (QML) algorithms. We propose to compare the results obtained using QML techniques with results using available classical ML algorithms.
| CERN group or section submitting a project proposal | gluoNNet & METU & CERN openlab |
|---|
Primary authors
Karolos Potamianos
(University of Oxford (GB))
Daniel Dobos
(Lancaster University (GB))
Bilge Demirkoz
(Middle East Technical University (TR))
Kristiane Novotny
(gluoNNet)
