Cargando…
Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment
A novel b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS Experiment. This talk presents the expected performance of the RNN based b-tagging in simulated $t \bar t$ events. The RNN based b-tagging processes properties of tracks associated to jets which...
Autor principal: | |
---|---|
Lenguaje: | eng |
Publicado: |
2017
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2262997 |
_version_ | 1780954162736922624 |
---|---|
author | Jiang, Zihao |
author_facet | Jiang, Zihao |
author_sort | Jiang, Zihao |
collection | CERN |
description | A novel b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS Experiment. This talk presents the expected performance of the RNN based b-tagging in simulated $t \bar t$ events. The RNN based b-tagging processes properties of tracks associated to jets which are represented in sequences. In contrast to traditional impact-parameter-based b-tagging algorithms which assume the tracks of jets are independent from each other, RNN based b-tagging can exploit the spatial and kinematic correlations of tracks which are initiated from the same b-hadrons. The neural network nature of the tagging algorithm also allows the flexibility of extending input features to include more track properties than can be effectively used in traditional algorithms. |
id | cern-2262997 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2017 |
record_format | invenio |
spelling | cern-22629972019-09-30T06:29:59Zhttp://cds.cern.ch/record/2262997engJiang, ZihaoIdentification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS ExperimentParticle Physics - ExperimentA novel b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS Experiment. This talk presents the expected performance of the RNN based b-tagging in simulated $t \bar t$ events. The RNN based b-tagging processes properties of tracks associated to jets which are represented in sequences. In contrast to traditional impact-parameter-based b-tagging algorithms which assume the tracks of jets are independent from each other, RNN based b-tagging can exploit the spatial and kinematic correlations of tracks which are initiated from the same b-hadrons. The neural network nature of the tagging algorithm also allows the flexibility of extending input features to include more track properties than can be effectively used in traditional algorithms.ATL-PHYS-SLIDE-2017-219oai:cds.cern.ch:22629972017-05-09 |
spellingShingle | Particle Physics - Experiment Jiang, Zihao Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title | Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title_full | Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title_fullStr | Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title_full_unstemmed | Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title_short | Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment |
title_sort | identification of jets containing b-hadrons with recurrent neural networks at the atlas experiment |
topic | Particle Physics - Experiment |
url | http://cds.cern.ch/record/2262997 |
work_keys_str_mv | AT jiangzihao identificationofjetscontainingbhadronswithrecurrentneuralnetworksattheatlasexperiment |