Cargando…

End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data

From particle identification to the discovery of the Higgs boson, deep learning algorithms have become an increasingly important tool for data analysis at the Large Hadron Collider (LHC). We present an innovative end-to-end deep learning approach for jet identification at the Compact Muon Solenoid (...

Descripción completa

Detalles Bibliográficos
Autores principales: Alison, John, An, Sitong, Bryant, Patrick, Burkle, Bjorn, Gleyzer, Sergei, Narain, Meenakshi, Paulini, Manfred, Poczos, Barnabas, Usai, Emanuele
Lenguaje:eng
Publicado: 2019
Materias:
Acceso en línea:http://cds.cern.ch/record/2698977
_version_ 1780964362353115136
author Alison, John
An, Sitong
Bryant, Patrick
Burkle, Bjorn
Gleyzer, Sergei
Narain, Meenakshi
Paulini, Manfred
Poczos, Barnabas
Usai, Emanuele
author_facet Alison, John
An, Sitong
Bryant, Patrick
Burkle, Bjorn
Gleyzer, Sergei
Narain, Meenakshi
Paulini, Manfred
Poczos, Barnabas
Usai, Emanuele
author_sort Alison, John
collection CERN
description From particle identification to the discovery of the Higgs boson, deep learning algorithms have become an increasingly important tool for data analysis at the Large Hadron Collider (LHC). We present an innovative end-to-end deep learning approach for jet identification at the Compact Muon Solenoid (CMS) experiment at the LHC. The method combines deep neural networks with low-level detector information, such as calorimeter energy deposits and tracking information, to build a discriminator to identify different particle species. Using two physics examples as references: electron vs. photon discrimination and quark vs. gluon discrimination, we demonstrate the performance of the end-to-end approach on simulated events with full detector geometry as available in the CMS Open Data. We also offer insights into the importance of the information extracted from various sub-detectors and describe how end-to-end techniques can be extended to event-level classification using information from the whole CMS detector.
id cern-2698977
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-26989772019-11-08T03:09:08Zhttp://cds.cern.ch/record/2698977engAlison, JohnAn, SitongBryant, PatrickBurkle, BjornGleyzer, SergeiNarain, MeenakshiPaulini, ManfredPoczos, BarnabasUsai, EmanueleEnd-to-end particle and event identification at the Large Hadron Collider with CMS Open Dataphysics.ins-detDetectors and Experimental Techniqueshep-exParticle Physics - ExperimentFrom particle identification to the discovery of the Higgs boson, deep learning algorithms have become an increasingly important tool for data analysis at the Large Hadron Collider (LHC). We present an innovative end-to-end deep learning approach for jet identification at the Compact Muon Solenoid (CMS) experiment at the LHC. The method combines deep neural networks with low-level detector information, such as calorimeter energy deposits and tracking information, to build a discriminator to identify different particle species. Using two physics examples as references: electron vs. photon discrimination and quark vs. gluon discrimination, we demonstrate the performance of the end-to-end approach on simulated events with full detector geometry as available in the CMS Open Data. We also offer insights into the importance of the information extracted from various sub-detectors and describe how end-to-end techniques can be extended to event-level classification using information from the whole CMS detector.arXiv:1910.07029oai:cds.cern.ch:26989772019-10-15
spellingShingle physics.ins-det
Detectors and Experimental Techniques
hep-ex
Particle Physics - Experiment
Alison, John
An, Sitong
Bryant, Patrick
Burkle, Bjorn
Gleyzer, Sergei
Narain, Meenakshi
Paulini, Manfred
Poczos, Barnabas
Usai, Emanuele
End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title_full End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title_fullStr End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title_full_unstemmed End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title_short End-to-end particle and event identification at the Large Hadron Collider with CMS Open Data
title_sort end-to-end particle and event identification at the large hadron collider with cms open data
topic physics.ins-det
Detectors and Experimental Techniques
hep-ex
Particle Physics - Experiment
url http://cds.cern.ch/record/2698977
work_keys_str_mv AT alisonjohn endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT ansitong endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT bryantpatrick endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT burklebjorn endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT gleyzersergei endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT narainmeenakshi endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT paulinimanfred endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT poczosbarnabas endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata
AT usaiemanuele endtoendparticleandeventidentificationatthelargehadroncolliderwithcmsopendata