Cargando…
ML Techniques for heavy flavour identification in CMS
<!--HTML-->Jet flavour identification is a fundamental component for the physics program of the LHC-based experiments. The presence of multiple flavours to be identified leads to a multiclass classification problem. Moreover, the classification of boosted jets has acquired an increasing import...
Autor principal: | |
---|---|
Lenguaje: | eng |
Publicado: |
2019
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2672563 |
_version_ | 1780962464706330624 |
---|---|
author | Bols, Emil Sorensen |
author_facet | Bols, Emil Sorensen |
author_sort | Bols, Emil Sorensen |
collection | CERN |
description | <!--HTML-->Jet flavour identification is a fundamental component for the physics program of the LHC-based experiments. The presence of multiple flavours to be identified leads to a multiclass classification problem. Moreover, the classification of boosted jets has acquired an increasing importance in the physics program of CMS. In this presentation we will present the performance on both simulated and real data of our latest resolved and boosted heavy flavour taggers as well as the future prospects for the evolution of these techniques and the technical strategies adopted to deploy them in the harsh computing environment of a large-scale HEP computing software stack. |
id | cern-2672563 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2019 |
record_format | invenio |
spelling | cern-26725632022-11-02T22:33:36Zhttp://cds.cern.ch/record/2672563engBols, Emil SorensenML Techniques for heavy flavour identification in CMS3rd IML Machine Learning WorkshopLPCC Workshops<!--HTML-->Jet flavour identification is a fundamental component for the physics program of the LHC-based experiments. The presence of multiple flavours to be identified leads to a multiclass classification problem. Moreover, the classification of boosted jets has acquired an increasing importance in the physics program of CMS. In this presentation we will present the performance on both simulated and real data of our latest resolved and boosted heavy flavour taggers as well as the future prospects for the evolution of these techniques and the technical strategies adopted to deploy them in the harsh computing environment of a large-scale HEP computing software stack.oai:cds.cern.ch:26725632019 |
spellingShingle | LPCC Workshops Bols, Emil Sorensen ML Techniques for heavy flavour identification in CMS |
title | ML Techniques for heavy flavour identification in CMS |
title_full | ML Techniques for heavy flavour identification in CMS |
title_fullStr | ML Techniques for heavy flavour identification in CMS |
title_full_unstemmed | ML Techniques for heavy flavour identification in CMS |
title_short | ML Techniques for heavy flavour identification in CMS |
title_sort | ml techniques for heavy flavour identification in cms |
topic | LPCC Workshops |
url | http://cds.cern.ch/record/2672563 |
work_keys_str_mv | AT bolsemilsorensen mltechniquesforheavyflavouridentificationincms AT bolsemilsorensen 3rdimlmachinelearningworkshop |