Cargando…
DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking
Tracking in high density environments, such as the core of TeV jets, is particularly challenging both because combinatorics quickly diverge and because tracks may not leave anymore individual hits but rather large clusters of merged signals in the innermost tracking detectors. In the CMS collaborati...
Autor principal: | |
---|---|
Lenguaje: | eng |
Publicado: |
2019
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2797737 |
_version_ | 1780972425107734528 |
---|---|
author | Bertacchi, Valerio |
author_facet | Bertacchi, Valerio |
author_sort | Bertacchi, Valerio |
collection | CERN |
description | Tracking in high density environments, such as the core of TeV jets, is particularly challenging both because combinatorics quickly diverge and because tracks may not leave anymore individual hits but rather large clusters of merged signals in the innermost tracking detectors. In the CMS collaboration this problem has been addressed in the past with cluster splitting algorithms, working layer by layer, followed by a pattern recognition step where a high number of candidate tracks are tested. Modern Deep Learning techniques can be used to better handle the problem by correlating information on multiple layers and directly providing proto-tracks without the need of an explicit cluster splitting algorithm. Preliminary results will be presented with ideas on how to further improve the algorithms. |
id | cern-2797737 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2019 |
record_format | invenio |
spelling | cern-27977372021-12-13T20:15:46Zhttp://cds.cern.ch/record/2797737engBertacchi, ValerioDeepCore: Convolutional Neural Network for high~$p_T$ jet trackingDetectors and Experimental TechniquesTracking in high density environments, such as the core of TeV jets, is particularly challenging both because combinatorics quickly diverge and because tracks may not leave anymore individual hits but rather large clusters of merged signals in the innermost tracking detectors. In the CMS collaboration this problem has been addressed in the past with cluster splitting algorithms, working layer by layer, followed by a pattern recognition step where a high number of candidate tracks are tested. Modern Deep Learning techniques can be used to better handle the problem by correlating information on multiple layers and directly providing proto-tracks without the need of an explicit cluster splitting algorithm. Preliminary results will be presented with ideas on how to further improve the algorithms.CMS-CR-2019-068oai:cds.cern.ch:27977372019-05-16 |
spellingShingle | Detectors and Experimental Techniques Bertacchi, Valerio DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title | DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title_full | DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title_fullStr | DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title_full_unstemmed | DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title_short | DeepCore: Convolutional Neural Network for high~$p_T$ jet tracking |
title_sort | deepcore: convolutional neural network for high~$p_t$ jet tracking |
topic | Detectors and Experimental Techniques |
url | http://cds.cern.ch/record/2797737 |
work_keys_str_mv | AT bertacchivalerio deepcoreconvolutionalneuralnetworkforhighptjettracking |