Please use this identifier to cite or link to this item:
https://hdl.handle.net/11147/12882
Title: | Identification of Hadronic Tau Lepton Decays Using a Deep Neural Network | Authors: | Tumasyan, A. Adam, W. Andrejkovic, J.W. Bergauer, T. Chatterjee, S. Dragicevic, M. Andreev, V. |
Keywords: | Calibration And Fitting Methods Cluster Finding Large Detector Systems For Particle And Astroparticle Physics Particle Identification Methods Pattern Recognition |
Publisher: | Institute of Physics | Abstract: | A new algorithm is presented to discriminate reconstructed hadronic decays of tau leptons (τ h) that originate from genuine tau leptons in the CMS detector against τ h candidates that originate from quark or gluon jets, electrons, or muons. The algorithm inputs information from all reconstructed particles in the vicinity of a τ h candidate and employs a deep neural network with convolutional layers to efficiently process the inputs. This algorithm leads to a significantly improved performance compared with the previously used one. For example, the efficiency for a genuine τ h to pass the discriminator against jets increases by 10-30% for a given efficiency for quark and gluon jets. Furthermore, a more efficient τ h reconstruction is introduced that incorporates additional hadronic decay modes. The superior performance of the new algorithm to discriminate against jets, electrons, and muons and the improved τ h reconstruction method are validated with LHC proton-proton collision data at s = 13 TeV. © 2022 CERN. | URI: | https://doi.org/10.1088/1748-0221/17/07/P07023 | ISSN: | 1748-0221 |
Appears in Collections: | Rectorate / Rektörlük Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
Show full item record
CORE Recommender
SCOPUSTM
Citations
45
checked on Apr 25, 2025
WEB OF SCIENCETM
Citations
37
checked on Apr 12, 2025
Page view(s)
188
checked on Apr 21, 2025
Download(s)
56
checked on Apr 21, 2025
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.