Boosted jet identification using particle candidates and deep neural networks

This note presents developments for the identification of hadronically decaying top quarks using deep neural networks in CMS. A new method that utilizes one dimensional convolutional neural networks based on jet constituent particles is proposed. Alternative methods using boosted decision trees base...

Descripción completa

Detalles Bibliográficos
Autor principal: CMS Collaboration
Lenguaje:eng
Publicado: 2017
Materias:
Detectors and Experimental Techniques
Acceso en línea:http://cds.cern.ch/record/2295725
_version_ 1780956706242560000
author CMS Collaboration
author_facet CMS Collaboration
author_sort CMS Collaboration
collection CERN
description This note presents developments for the identification of hadronically decaying top quarks using deep neural networks in CMS. A new method that utilizes one dimensional convolutional neural networks based on jet constituent particles is proposed. Alternative methods using boosted decision trees based on jet observables are compared. The new method shows significant improvement in performance.
id cern-2295725
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2017
record_format invenio
spelling cern-22957252019-09-30T06:29:59Zhttp://cds.cern.ch/record/2295725engCMS CollaborationBoosted jet identification using particle candidates and deep neural networksDetectors and Experimental TechniquesThis note presents developments for the identification of hadronically decaying top quarks using deep neural networks in CMS. A new method that utilizes one dimensional convolutional neural networks based on jet constituent particles is proposed. Alternative methods using boosted decision trees based on jet observables are compared. The new method shows significant improvement in performance.CMS-DP-2017-049CERN-CMS-DP-2017-049oai:cds.cern.ch:22957252017-11-14
spellingShingle Detectors and Experimental Techniques
CMS Collaboration
Boosted jet identification using particle candidates and deep neural networks
title Boosted jet identification using particle candidates and deep neural networks
title_full Boosted jet identification using particle candidates and deep neural networks
title_fullStr Boosted jet identification using particle candidates and deep neural networks
title_full_unstemmed Boosted jet identification using particle candidates and deep neural networks
title_short Boosted jet identification using particle candidates and deep neural networks
title_sort boosted jet identification using particle candidates and deep neural networks
topic Detectors and Experimental Techniques
url http://cds.cern.ch/record/2295725
work_keys_str_mv AT cmscollaboration boostedjetidentificationusingparticlecandidatesanddeepneuralnetworks

Ejemplares similares