Development of a vertex finding algorithm using Recurrent Neural Network

被引：3

作者：

Goto, Kiichi ^{[1
,4
,6
]}

Suehara, Taikan ^{[1
,2
,3
,4
,6
]}

Yoshioka, Tamaki ^{[1
,2
,3
,4
,6
]}

Kurata, Masakazu ^{[4
,6
]}

Nagahara, Hajime ^{[4
,5
,6
]}

Nakashima, Yuta ^{[4
,5
,6
]}

Takemura, Noriko ^{[4
,5
,6
]}

Iwasaki, Masako ^{[4
,5
,6
,7
,8
]}

机构：

[1] Kyushu Univ, Grad Sch Sci, Dept Phys, Fukuoka, Japan

[2] Kyushu Univ, Fac Sci, Dept Phys, Fukuoka, Japan

[3] Kyushu Univ, Res Ctr Adv Particle Phys RCAPP, Fukuoka, Japan

[4] Univ Tokyo, Grad Sch Sci, Dept Phys, Tokyo, Japan

[5] Osaka Univ, Inst Databil Sci IDS, Suita, Japan

[6] Osaka City Univ, Grad Sch Sci, Dept Math & Phys, Osaka, Japan

[7] Osaka City Univ, Nambu Yoichiro Inst Theoret & Expt Phys NITEP, Osaka, Japan

[8] Osaka Univ, Res Ctr Nucl Phys RCNP, Suita, Japan

来源：

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT | 2023年 / 1047卷

关键词：

International linear collider; Vertex finding; Recurrent Neural Network; Attention; LHC;

D O I：

10.1016/j.nima.2022.167836

中图分类号：

TH7 [仪器、仪表];

学科分类号：

0804 ; 080401 ; 081102 ;

摘要：

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.

引用

页数：9

共 50 条

[1] Bluetooth Direction Finding using Recurrent Neural Network
Babakhani, Pedram
Merk, Timon
Mahlig, Matthias
Sarris, Ioannis
Kalogiros, Dimitris
Karlsson, Peter
INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN 2021), 2021,
[2] Simulating Reservoir Operation Using a Recurrent Neural Network Algorithm
Zhang, Di
Peng, Qidong
Lin, Junqiang
Wang, Dongsheng
Liu, Xuefei
Zhuang, Jiangbo
WATER, 2019, 11 (04)
[3] Using the Metropolis algorithm to explore the loss surface of a recurrent neural network
Casert, Corneel
Whitelam, Stephen
Journal of Chemical Physics, 2024, 161 (23):
[4] Adaptive recurrent neural network control using a structure adaptation algorithm
Hsu, Chun-Fei
NEURAL COMPUTING & APPLICATIONS, 2009, 18 (02): : 115 - 125
[5] Adaptive recurrent neural network control using a structure adaptation algorithm
Chun-Fei Hsu
Neural Computing and Applications, 2009, 18 : 115 - 125
[6] Blind Equalization Using a Novel Recurrent Neural Network Training Algorithm
Liang Qilian Zhou Zheng and Liu Zemin (College of Telecom Engineering
TheJournalofChinaUniversitiesofPostsandTelecommunications, 1997, (02) : 47 - 49
[7] Development of input variable selection and structural optimization algorithm for recurrent neural network
Zhang, Mengyan
Sui, Lin
Sun, Kai
2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 8094 - 8099
[8] Novel recurrent neural network and its algorithm
Northeastern Univ, China
Kongzhi yu Juece Control Decis, Suppl (467-471):
[9] A novel recurrent neural network and its algorithm
Wang, JH
Jin, QB
Gu, SS
LOW COST AUTOMATION 1998 (LCA'98), 1999, : 249 - 253
[10] PRIMARY VERTEX FINDING IN PROTON-ANTIPROTON EVENTS WITH A NEURAL NETWORK SIMULATION
LINDSEY, CS
DENBY, B
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1991, 302 (02): : 217 - 226

← 1 2 3 4 5 →