Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data
Abstract
Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.
- Authors:
-
- Carnegie Mellon Univ., Pittsburgh, PA (United States)
- Brown Univ., Providence, RI (United States)
- Birla Institute of Technology and Science (BITS) Pilani, Goa (India)
- Univ. of Alabama, Tuscaloosa, AL (United States)
- Publication Date:
- Research Org.:
- Carnegie Mellon Univ., Pittsburgh, PA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- OSTI Identifier:
- 1837660
- Grant/Contract Number:
- SC0010118
- Resource Type:
- Accepted Manuscript
- Journal Name:
- EPJ Web of Conferences (Online)
- Additional Journal Information:
- Journal Name: EPJ Web of Conferences (Online); Journal Volume: 251; Conference: 25. International Conference on Computing in High Energy and Nuclear Physics (CHEP 2021), Paris (France) (Held Virtually), 17-21 May 2021; Journal ID: ISSN 2100-014X
- Publisher:
- EDP Sciences
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
Citation Formats
Andrews, Michael, Burkle, Bjorn, Chaudhari, Shravan, Di Croce, Davide, Gleyzer, Sergei, Heintz, Ulrich, Narain, Meenakshi, Paulini, Manfred, and Usai, Emanuele. Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data. United States: N. p., 2021.
Web. doi:10.1051/epjconf/202125103057.
Andrews, Michael, Burkle, Bjorn, Chaudhari, Shravan, Di Croce, Davide, Gleyzer, Sergei, Heintz, Ulrich, Narain, Meenakshi, Paulini, Manfred, & Usai, Emanuele. Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data. United States. https://doi.org/10.1051/epjconf/202125103057
Andrews, Michael, Burkle, Bjorn, Chaudhari, Shravan, Di Croce, Davide, Gleyzer, Sergei, Heintz, Ulrich, Narain, Meenakshi, Paulini, Manfred, and Usai, Emanuele. Mon .
"Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data". United States. https://doi.org/10.1051/epjconf/202125103057. https://www.osti.gov/servlets/purl/1837660.
@article{osti_1837660,
title = {Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data},
author = {Andrews, Michael and Burkle, Bjorn and Chaudhari, Shravan and Di Croce, Davide and Gleyzer, Sergei and Heintz, Ulrich and Narain, Meenakshi and Paulini, Manfred and Usai, Emanuele},
abstractNote = {Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.},
doi = {10.1051/epjconf/202125103057},
journal = {EPJ Web of Conferences (Online)},
number = ,
volume = 251,
place = {United States},
year = {Mon Aug 23 00:00:00 EDT 2021},
month = {Mon Aug 23 00:00:00 EDT 2021}
}
Works referenced in this record:
End-to-end jet classification of quarks and gluons with the CMS Open Data
journal, October 2020
- Andrews, M.; Alison, J.; An, S.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 977
Deep Residual Learning for Image Recognition
conference, June 2016
- He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Advances in flash memory SSD technology for enterprise database applications
conference, June 2009
- Lee, Sang-Won; Moon, Bongki; Park, Chanik
- SIGMOD/PODS '09: International Conference on Management of Data, Proceedings of the 2009 ACM SIGMOD International Conference on Management of data
End-to-End Physics Event Classification with CMS Open Data: Applying Image-Based Deep Learning to Detector Data for the Direct Classification of Collision Events at the LHC
journal, March 2020
- Andrews, M.; Paulini, M.; Gleyzer, S.
- Computing and Software for Big Science, Vol. 4, Issue 1
The anti- k t jet clustering algorithm
journal, April 2008
- Cacciari, Matteo; Salam, Gavin P.; Soyez, Gregory
- Journal of High Energy Physics, Vol. 2008, Issue 04