CaltechAUTHORS
  A Caltech Library Service

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

Farrell, Steven and Anderson, Dustin and Calafiura, Paolo and Cerati, Giuseppe and Gray, Lindsey and Kowalkowski, Jim and Mudigonda, Mayur and Prabhat, Mr. and Spentzouris, Panagiotis and Spiropoulou, Maria and Tsaris, Aristeidis and Vlimant, Jean-Roch and Zheng, Stephan (2017) The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking. EPJ Web of Conferences, 150 . Art. No. 00003. ISSN 2100-014X. http://resolver.caltech.edu/CaltechAUTHORS:20180321-110952123

[img] PDF - Published Version
Creative Commons Attribution.

2161Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180321-110952123

Abstract

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. We will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1051/epjconf/201715000003DOIArticle
https://www.epj-conferences.org/articles/epjconf/abs/2017/19/epjconf_ctdw2017_00003/epjconf_ctdw2017_00003.htmlPublisherArticle
ORCID:
AuthorORCID
Spiropoulou, Maria0000-0001-8172-7081
Additional Information:© 2017 The Authors, published by EDP Sciences. This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Published online: 8 August 2017. The authors would like to thank the funding agencies DOE ASCR and COMP HEP for supporting this work, as well as the numerous tracking experts from ATLAS and CMS who have shared insights and experience.
Group:CMS@Caltech
Funders:
Funding AgencyGrant Number
Department of Energy (DOE)UNSPECIFIED
CompHEPUNSPECIFIED
Record Number:CaltechAUTHORS:20180321-110952123
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180321-110952123
Official Citation:The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking. Steven Farrell, Dustin Anderson, Paolo Calafiura, Giuseppe Cerati, Lindsey Gray, Jim Kowalkowski, Mayur Mudigonda, Prabhat, Panagiotis Spentzouris, Maria Spiropoulou, Aristeidis Tsaris, Jean-Roch Vlimant, Stephan Zheng. EPJ Web Conf. 150 00003 (2017). DOI: 10.1051/epjconf/201715000003
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:85399
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:26 Mar 2018 13:36
Last Modified:26 Mar 2018 13:36

Repository Staff Only: item control page