28 July 2020 to 6 August 2020
virtual conference
Europe/Prague timezone

Tau identification exploiting deep learning techniques

29 Jul 2020, 18:20
virtual conference

virtual conference

Talk 12. Operation, Performance and Upgrade of Present Detectors Operation, Performance and Upgrade of Present Detectors


Andrea Cardini (DESY) Andrea Cardini (Deutsches Elektronen-Synchrotron (DE))


The recently deployed DeepTau algorithm for the discrimination of taus from light flavor quark or gluon induced jets, electrons, or muons is an ideal example for the exploitation of modern deep learning neural network techniques. With the current algorithm a suppression of miss-identification rates by factors of two and more have been achieved for the same identification efficiency for taus as for the MVA identification algorithms used for the LHC Run-1, leading to significant performance gains for many tau related analyses. The algorithm and its performance will be discussed.

Secondary track (number) 13.

Primary author

Presentation Materials