Machine learning techniques for heavy flavour identification

Reliable and performant heavy flavour identification is of prime importance for the physics program of the CMS experiment. During the last years the CMS collaboration has dedicated a considerable effort to improve and expand its capabilities in this sector by applying several machine learning techni...

Descripción completa

Detalles Bibliográficos
Autor principal: Chazin Quero, Barbara
Lenguaje:eng
Publicado: 2018
Materias:
Detectors and Experimental Techniques
Acceso en línea:https://dx.doi.org/10.22323/1.321.0066
http://cds.cern.ch/record/2638064
_version_ 1780959959589060608
author Chazin Quero, Barbara
author_facet Chazin Quero, Barbara
author_sort Chazin Quero, Barbara
collection CERN
description Reliable and performant heavy flavour identification is of prime importance for the physics program of the CMS experiment. During the last years the CMS collaboration has dedicated a considerable effort to improve and expand its capabilities in this sector by applying several machine learning techniques well established in industry, but still experimental in HEP. The poster will focus on a selection of these techniques and describe the implementation details as well as the resulting gains.
id cern-2638064
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-26380642019-10-15T15:20:58Zdoi:10.22323/1.321.0066http://cds.cern.ch/record/2638064engChazin Quero, BarbaraMachine learning techniques for heavy flavour identificationDetectors and Experimental TechniquesReliable and performant heavy flavour identification is of prime importance for the physics program of the CMS experiment. During the last years the CMS collaboration has dedicated a considerable effort to improve and expand its capabilities in this sector by applying several machine learning techniques well established in industry, but still experimental in HEP. The poster will focus on a selection of these techniques and describe the implementation details as well as the resulting gains.CMS-CR-2018-196oai:cds.cern.ch:26380642018-09-04
spellingShingle Detectors and Experimental Techniques
Chazin Quero, Barbara
Machine learning techniques for heavy flavour identification
title Machine learning techniques for heavy flavour identification
title_full Machine learning techniques for heavy flavour identification
title_fullStr Machine learning techniques for heavy flavour identification
title_full_unstemmed Machine learning techniques for heavy flavour identification
title_short Machine learning techniques for heavy flavour identification
title_sort machine learning techniques for heavy flavour identification
topic Detectors and Experimental Techniques
url https://dx.doi.org/10.22323/1.321.0066
http://cds.cern.ch/record/2638064
work_keys_str_mv AT chazinquerobarbara machinelearningtechniquesforheavyflavouridentification

Ejemplares similares