Cargando…

A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton

<!--HTML-->The optimization of reconstruction algorithms has become a key aspect in LHCb as it is currently undergoing a major upgrade that will considerably increase the data processing rate. Aiming to accelerate the second most time consuming reconstruction process of the trigger, we propose...

Descripción completa

Detalles Bibliográficos
Autor principal: Valls Canudas, Nuria
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:http://cds.cern.ch/record/2766981
_version_ 1780971253105950720
author Valls Canudas, Nuria
author_facet Valls Canudas, Nuria
author_sort Valls Canudas, Nuria
collection CERN
description <!--HTML-->The optimization of reconstruction algorithms has become a key aspect in LHCb as it is currently undergoing a major upgrade that will considerably increase the data processing rate. Aiming to accelerate the second most time consuming reconstruction process of the trigger, we propose an alternative reconstruction algorithm for the Electromagnetic Calorimeter of LHCb. Together with the use of deep learning techniques and the understanding of the current algorithm, our proposal decomposes the reconstruction process into small parts that benefit the generalized learning of small neural network architectures and simplifies the training dataset. This approach takes as input the full simulation data of the calorimeter and outputs a list of reconstructed clusters in a nearly constant time without any dependency in the event complexity.
id cern-2766981
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27669812022-11-02T22:25:52Zhttp://cds.cern.ch/record/2766981engValls Canudas, NuriaA Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton25th International Conference on Computing in High Energy & Nuclear PhysicsConferences<!--HTML-->The optimization of reconstruction algorithms has become a key aspect in LHCb as it is currently undergoing a major upgrade that will considerably increase the data processing rate. Aiming to accelerate the second most time consuming reconstruction process of the trigger, we propose an alternative reconstruction algorithm for the Electromagnetic Calorimeter of LHCb. Together with the use of deep learning techniques and the understanding of the current algorithm, our proposal decomposes the reconstruction process into small parts that benefit the generalized learning of small neural network architectures and simplifies the training dataset. This approach takes as input the full simulation data of the calorimeter and outputs a list of reconstructed clusters in a nearly constant time without any dependency in the event complexity.oai:cds.cern.ch:27669812021
spellingShingle Conferences
Valls Canudas, Nuria
A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title_full A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title_fullStr A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title_full_unstemmed A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title_short A Deep Learning approach to LHCb Calorimeter reconstruction using a Cellular Automaton
title_sort deep learning approach to lhcb calorimeter reconstruction using a cellular automaton
topic Conferences
url http://cds.cern.ch/record/2766981
work_keys_str_mv AT vallscanudasnuria adeeplearningapproachtolhcbcalorimeterreconstructionusingacellularautomaton
AT vallscanudasnuria 25thinternationalconferenceoncomputinginhighenergynuclearphysics
AT vallscanudasnuria deeplearningapproachtolhcbcalorimeterreconstructionusingacellularautomaton