Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques

Show full item record



Permalink

http://hdl.handle.net/10138/321572

Citation

The CMS Collaboration , Eerola , P , Forthomme , L , Kirschenmann , H , Osterberg , K , Voutilainen , M , Garcia , F , Havukainen , J , Heikkila , J K , Kim , M , Kinnunen , R , Lampen , T , Lassila-Perini , K , Laurila , S , Lehti , S , Linden , T , Luukka , P , Mäenpää , T , Siikonen , H , Tuominen , E , Tuominiemi , J , Viinikainen , J , Pekkanen , J , Karimäki , V , Tuuva , T , Sirunyan , A M & Tumasyan , A 2020 , ' Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques ' , Journal of Instrumentation , vol. 15 , no. 6 , 06005 . https://doi.org/10.1088/1748-0221/15/06/P06005

Title: Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
Author: The CMS collaboration; Eerola, P.; Forthomme, L.; Kirschenmann, H.; Osterberg, K.; Voutilainen, M.; Garcia, F.; Havukainen, J.; Heikkila, J. K.; Kim, M.; Kinnunen, R.; Lampen, T.; Lassila-Perini, K.; Laurila, S.; Lehti, S.; Linden, T.; Luukka, P.; Mäenpää, T.; Siikonen, H.; Tuominen, E.; Tuominiemi, J.; Viinikainen, J.; Pekkanen, J.; Karimäki, V.; Tuuva, T.; Sirunyan, A. M.; Tumasyan, A.
Contributor organization: Department of Physics
Helsinki Institute of Physics
Eija Tuominen / Principal Investigator
Date: 2020-06
Language: eng
Number of pages: 87
Belongs to series: Journal of Instrumentation
ISSN: 1748-0221
DOI: https://doi.org/10.1088/1748-0221/15/06/P06005
URI: http://hdl.handle.net/10138/321572
Abstract: Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at root S = 13 TeV, corresponding to an integrated luminosity of 35.9 fb(-1). Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
Subject: 114 Physical sciences
Peer reviewed: Yes
Rights: cc_by
Usage restriction: openAccess
Self-archived version: publishedVersion


Files in this item

Total number of downloads: Loading...

Files Size Format View
Sirunyan_2020_J._Inst._15_P06005.pdf 5.349Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record