Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector

A study on the use of Graph Neural Networks for the selection of$t\bar{t}t\bar{t}$ events in the ATLAS detector is presented. Data used is the Monte-Carlo simulated proton-proton collision events at $\sqrt{s} = 13$ TeV. The analysis is only concerned with the same-sign multilepton channel. After opt...

Descripción completa

Detalles Bibliográficos
Autor principal: Ananiashvili, Vakhtang
Lenguaje:eng
Publicado: 2022
Materias:
Accelerators and Storage Rings
Acceso en línea:http://cds.cern.ch/record/2802704
_version_ 1780972756650688512
author Ananiashvili, Vakhtang
author_facet Ananiashvili, Vakhtang
author_sort Ananiashvili, Vakhtang
collection CERN
description A study on the use of Graph Neural Networks for the selection of$t\bar{t}t\bar{t}$ events in the ATLAS detector is presented. Data used is the Monte-Carlo simulated proton-proton collision events at $\sqrt{s} = 13$ TeV. The analysis is only concerned with the same-sign multilepton channel. After optimization, GNNs achieved a performance of AUC = $0.8744 \pm 0.0017$ which is an improvement over the previous studies conducted on the same data using Boosted Decision Trees and Feedforward Neural Networks.
id cern-2802704
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2022
record_format invenio
spelling cern-28027042022-03-15T22:43:49Zhttp://cds.cern.ch/record/2802704engAnaniashvili, VakhtangImproving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detectorAccelerators and Storage RingsA study on the use of Graph Neural Networks for the selection of$t\bar{t}t\bar{t}$ events in the ATLAS detector is presented. Data used is the Monte-Carlo simulated proton-proton collision events at $\sqrt{s} = 13$ TeV. The analysis is only concerned with the same-sign multilepton channel. After optimization, GNNs achieved a performance of AUC = $0.8744 \pm 0.0017$ which is an improvement over the previous studies conducted on the same data using Boosted Decision Trees and Feedforward Neural Networks.CERN-THESIS-2021-291BONN-IB-2022-01oai:cds.cern.ch:28027042022-03-01T08:47:12Z
spellingShingle Accelerators and Storage Rings
Ananiashvili, Vakhtang
Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title_full Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title_fullStr Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title_full_unstemmed Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title_short Improving the $t\bar{t}t\bar{t}$ event selection with Graph Neural Networks in multilepton final states at the ATLAS detector
title_sort improving the $t\bar{t}t\bar{t}$ event selection with graph neural networks in multilepton final states at the atlas detector
topic Accelerators and Storage Rings
url http://cds.cern.ch/record/2802704
work_keys_str_mv AT ananiashvilivakhtang improvingthetbarttbarteventselectionwithgraphneuralnetworksinmultileptonfinalstatesattheatlasdetector

Ejemplares similares