Searching. Please wait…
1582
37
171
29406
4423
2606
347
392
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 ?s = 13TeV, 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.
Fuente: Journal of instrumentation, 2020, 15, P06005
Publisher: Institute of Physics
Publication date: 01/06/2020
No. of pages: 88
Publication type: Article
DOI: 10.1088/1748-0221/15/06/P06005
ISSN: 1748-0221
Publication Url: https://doi.org/10.1088/1748-0221/15/06/P06005
Google Scholar
Citations
Read publication
SIRUNYAN, A. M.
JOSE IBAN CABRILLO BARTOLOME
ALICIA CALDERON TAZON
BARBARA CHAZIN QUERO
JORGE DUARTE CAMPDERROS
MARCOS FERNANDEZ GARCIA
PEDRO JOSE FERNANDEZ MANTECA
ANDREA GARCIA ALONSO
GERVASIO GOMEZ GRAMUGLIO
CELSO MARTINEZ RIVERO
PABLO MARTINEZ RUIZ DEL ARBOL
FRANCISCO MATORRAS WEINIG
JONATAN PIEDRA GOMEZ
CEDRIC GERALD PRIEELS
MARIA TERESA RODRIGO ANORO
ALBERTO RUIZ JIMENO
LORENZO RUSSO
LUCA SCODELLARO
IVAN VILA ALVAREZ
JESUS MANUEL VIZAN GARCIA
Back