TY - JOUR
T1 - Development of a vertex finding algorithm using Recurrent Neural Network
AU - Goto, Kiichi
AU - Suehara, Taikan
AU - Yoshioka, Tamaki
AU - Kurata, Masakazu
AU - Nagahara, Hajime
AU - Nakashima, Yuta
AU - Takemura, Noriko
AU - Iwasaki, Masako
N1 - Funding Information:
The authors would appreciate D. Jeans and M. Meyer for useful comments. We would also like to thank the LCC generator working group and the ILD software working group for providing the simulation and reconstruction tools and producing the Monte Carlo samples used in this study. This work has benefited from computing services provided by the ILC Virtual Organization, supported by the national resource providers of the EGI Federation and the Open Science GRID . This work is done in collaboration with the RCNP Project “Application of deep learning to accelerator experiments”. Furthermore this work is supported by the U.S.-Japan Science and Technology Cooperation Program in High Energy Physics .
Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2023/2
Y1 - 2023/2
N2 - Deep learning is a rapidly-evolving technology with the possibility to significantly improve the physics reach of collider experiments. In this study we developed a novel vertex finding algorithm for future lepton colliders such as the International Linear Collider. We deploy two networks: one consists of simple fully-connected layers to look for vertex seeds from track pairs, and the other is a customized Recurrent Neural Network with an attention mechanism and an encoder–decoder structure to associate tracks to the vertex seeds. The performance of the vertex finder is compared with the standard ILC vertex reconstruction algorithm.
AB - Deep learning is a rapidly-evolving technology with the possibility to significantly improve the physics reach of collider experiments. In this study we developed a novel vertex finding algorithm for future lepton colliders such as the International Linear Collider. We deploy two networks: one consists of simple fully-connected layers to look for vertex seeds from track pairs, and the other is a customized Recurrent Neural Network with an attention mechanism and an encoder–decoder structure to associate tracks to the vertex seeds. The performance of the vertex finder is compared with the standard ILC vertex reconstruction algorithm.
UR - http://www.scopus.com/inward/record.url?scp=85144285362&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85144285362&partnerID=8YFLogxK
U2 - 10.1016/j.nima.2022.167836
DO - 10.1016/j.nima.2022.167836
M3 - Article
AN - SCOPUS:85144285362
SN - 0168-9002
VL - 1047
JO - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
JF - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
M1 - 167836
ER -