DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets

Mostrar otras versiones (4)

<!--HTML-->We present a customized neural network architecture for both, slim and fat jet tagging. It is based on the idea to keep the concept of physics objects, like particle flow particles, as a core element of the network architecture. The deep learning algorithm works for most of the comm...

Descripción completa

Detalles Bibliográficos
Autores principales: Gouskos, Loukas, Qu, Huilin, Stoye, Markus, Kieseler, Jan, Verzetti, Mauro
Lenguaje:eng
Publicado: 2018
Materias:
Machine Learning
Acceso en línea:http://cds.cern.ch/record/2313229
_version_ 1780958038744629248
author Gouskos, Loukas
Qu, Huilin
Stoye, Markus
Kieseler, Jan
Verzetti, Mauro
author_facet Gouskos, Loukas
Qu, Huilin
Stoye, Markus
Kieseler, Jan
Verzetti, Mauro
author_sort Gouskos, Loukas
collection CERN
description <!--HTML-->We present a customized neural network architecture for both, slim and fat jet tagging. It is based on the idea to keep the concept of physics objects, like particle flow particles, as a core element of the network architecture. The deep learning algorithm works for most of the common jet classes, i.e. b, c, usd and gluon jets for slim jets and W, Z, H, QCD and top classes for fat jets. The developed architecture promising gains in performance as shown in simulation of the CMS collaboration. Currently the tagger is under test in real data in the CMS experiment.
id cern-2313229
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-23132292022-11-02T22:34:02Zhttp://cds.cern.ch/record/2313229engGouskos, LoukasQu, HuilinStoye, MarkusKieseler, JanVerzetti, MauroDeepJet: a deep-learned multiclass jet-tagger for slim and fat jets2nd IML Machine Learning WorkshopMachine Learning<!--HTML-->We present a customized neural network architecture for both, slim and fat jet tagging. It is based on the idea to keep the concept of physics objects, like particle flow particles, as a core element of the network architecture. The deep learning algorithm works for most of the common jet classes, i.e. b, c, usd and gluon jets for slim jets and W, Z, H, QCD and top classes for fat jets. The developed architecture promising gains in performance as shown in simulation of the CMS collaboration. Currently the tagger is under test in real data in the CMS experiment.oai:cds.cern.ch:23132292018
spellingShingle Machine Learning
Gouskos, Loukas
Qu, Huilin
Stoye, Markus
Kieseler, Jan
Verzetti, Mauro
DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title_full DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title_fullStr DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title_full_unstemmed DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title_short DeepJet: a deep-learned multiclass jet-tagger for slim and fat jets
title_sort deepjet: a deep-learned multiclass jet-tagger for slim and fat jets
topic Machine Learning
url http://cds.cern.ch/record/2313229
work_keys_str_mv AT gouskosloukas deepjetadeeplearnedmulticlassjettaggerforslimandfatjets
AT quhuilin deepjetadeeplearnedmulticlassjettaggerforslimandfatjets
AT stoyemarkus deepjetadeeplearnedmulticlassjettaggerforslimandfatjets
AT kieselerjan deepjetadeeplearnedmulticlassjettaggerforslimandfatjets
AT verzettimauro deepjetadeeplearnedmulticlassjettaggerforslimandfatjets
AT gouskosloukas 2ndimlmachinelearningworkshop
AT quhuilin 2ndimlmachinelearningworkshop
AT stoyemarkus 2ndimlmachinelearningworkshop
AT kieselerjan 2ndimlmachinelearningworkshop
AT verzettimauro 2ndimlmachinelearningworkshop

Ejemplares similares