Filters








53 Hits in 2.4 sec

The TrackML high-energy physics tracking challenge on Kaggle

Moritz Kiehn, Sabrina Amrouche, Paolo Calafiura, Victor Estrade, Steven Farrell, Cécile Germain, Vava Gligorov, Tobias Golling, Heather Gray, Isabelle Guyon, Mikhail Hushchyn, Vincenzo Innocente (+11 others)
2019 EPJ Web of Conferences  
To reach out to computer science specialists, a tracking machine learning challenge (TrackML) was set up on Kaggle by a team of ATLAS, CMS, and LHCb physicists tracking experts and computer scientists  ...  The High-Luminosity LHC (HL-LHC) is expected to reach unprecedented collision intensities, which in turn will greatly increase the complexity of tracking within the event reconstruction.  ...  We are very grateful to our generous sponsors without which the challenges would  ... 
doi:10.1051/epjconf/201921406037 fatcat:drsstpitlbblba65gcyoeyg62u

Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking [article]

Xiangyang Ju
2021 arXiv   pre-print
The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity  ...  This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS  ...  Introduction Charged particle tracking plays an essential role in High-Energy Physics (HEP), including particle identification and kinematics, vertex finding, lepton reconstruction, and flavor jet tagging  ... 
arXiv:2103.06995v2 fatcat:d5jsnbocijhc7izr54ugbjskxe

The TrackML challenge

David Rousseau, Sabrina Amrouche, Paolo Calafiura, Steven Farrell, Cécile Germain, Vladimir Gligorov, Tobias Golling, Heather Gray, Isabelle Guyon, Mikhail Hushchyn, David Rousseau, Sabrina Amrouche (+3 others)
2018 The TrackML challenge. NIPS 2018-32nd Annual Conference on Neural Information Processing Systems   unpublished
We call our new challenge "TrackML", for Tracking trajectories of particles with Machine Learning.  ...  Recently, several challenges in climate science, astrophysics, high energy physics, and chemistry have been organized as reported at the NIPS 2017 "challenges in machine learning" workshop 1 dedicated  ... 
fatcat:ecq3zytqhbgfpgfx7gjwx7xuzm

Particle Track Reconstruction with Quantum Algorithms [article]

Cenk Tüysüz, Federico Carminati, Bilge Demirköz, Daniel Dobos, Fabio Fracas, Kristiane Novotny, Karolos Potamianos, Sofia Vallecorsa, Jean-Roch Vlimant
2020 arXiv   pre-print
Accurate determination of particle track reconstruction parameters will be a major challenge for the High Luminosity Large Hadron Collider (HL-LHC) experiments.  ...  Thus, the reconstruction of charged particle tracks will be a major challenge to the correct interpretation of the HL-LHC data.  ...  This work was partially supported by Turkish Atomic Energy Authority (TAEK) (Grant No: 2017TAEKCERN-A5.H6.F2.15). Cenk Tüysüz thanks Oral Okan and Egemen Sert from STB for their valuable discussions.  ... 
arXiv:2003.08126v1 fatcat:rsdkmbzwjvg7xh6lml4hpnlaty

TrackML : a tracking Machine Learning challenge

Tobias Golling, Sabrina Amrouche, Moritz Kiehn, Paolo Calafiura, Steven Farrell, Heather M. Gray, Victor Estrade, Cécile Germain, Vava Gligorov, Isabelle Guyon, Mikhail Hushchyn, Andrey Ustyuzhanin (+6 others)
2019 Proceedings of The 39th International Conference on High Energy Physics — PoS(ICHEP2018)   unpublished
We are very grateful to our generous sponsors without which the challenges would not  ...  The 39th International Conference on High Energy Physics (ICHEP2018) 4-11 July, 2018 Seoul, Korea * Speaker.  ...  However, variations in track efficiency as a function of η are observed. Conclusion Overall the TrackML challenge was very well received by the Kaggle community with high levels of participation.  ... 
doi:10.22323/1.340.0159 fatcat:26svq2nkrfdevoxl3ojd4z7tty

Particle Track Reconstruction with Quantum Algorithms

Cenk Tüysüz, Federico Carminati, Bilge Demirköz, Daniel Dobos, Fabio Fracas, Kristiane Novotny, Karolos Potamianos, Sofia Vallecorsa, Jean-Roch Vlimant, C. Doglioni, D. Kim, G.A. Stewart (+3 others)
2020 EPJ Web of Conferences  
Accurate determination of particle track reconstruction parameters will be a major challenge for the High Luminosity Large Hadron Collider (HL-LHC) experiments.  ...  Thus, the reconstruction of charged particle tracks will be a major challenge to the correct interpretation of the HL-LHC data.  ...  The HepTrkX team proposed a Graph Neural Network implementation for particle track reconstruction that uses the kaggle TrackML challenge dataset [3, 7] .  ... 
doi:10.1051/epjconf/202024509013 fatcat:f6fpcitw45bh3gqczg55gkqwky

A pattern recognition algorithm for quantum annealers [article]

Frederic Bapst, Wahid Bhimji, Paolo Calafiura, Heather Gray, Wim Lavrijsen, Lucy Linder
2019 arXiv   pre-print
The reconstruction of charged particles will be a key computing challenge for the high-luminosity Large Hadron Collider (HL-LHC) where increased data rates lead to large increases in running time for current  ...  At track densities comparable with current LHC conditions, our approach achieves physics performance competitive with state-of-the-art pattern recognition algorithms.  ...  needed in quantum computers to solve problems in high-energy physics.  ... 
arXiv:1902.08324v1 fatcat:unqdp23syndxngjm4cz3rs73u4

Quantum annealing algorithms for track pattern recognition

Alex Smith, Heather Gray, Junichi Tanaka, Koji Terashi, Lucy Linder, Masahiko Saito, Paolo Calafiura, Ryu Sawada, Wim Lavrijsen, Yasuyuki Okumura
2019 Zenodo  
We will conclude with future perspectives on using annealing-based algorithms for pattern recognition in high-energy physics experiments.  ...  The pattern recognition of the trajectories of charged particles is at the core of the computing challenge for the HL-LHC, which is currently the center of a very active area of research.  ...  (2026~) Track reconstruction • Find the correct set of hits belonging to the same particle ○ Hits are distributed according to known physics rule: helix curve, scattering with material… Large QUBOs  ... 
doi:10.5281/zenodo.3599355 fatcat:tfu3xhxue5dvphj773cqopcb2q

CTD2020: A Quantum Graph Network Approach to Particle Track Reconstruction

Cenk Tüysüz, Bilge Demirkoz, Daniel Dobos, Fabio Fracas, Federico Carminati, Jean-Roch Vlimant, Karolos Potamianos, Kristiane Novotny, Sofia Vallecorsa
2020 Zenodo  
In previous work, we have shown a first attempt of Quantum Computing to Graph Neural Networks for track reconstruction of particles.  ...  It has been demonstrated previously by HEP.TrkX using TrackML datasets, that graph neural networks, processing events as a graph connecting track measurements, are a promising solution and can reduce the  ...  This work was partially supported by Turkish Atomic Energy Authority (TAEK) (Grant No: 2017TAEKCERN-A5.H6.F2.15).  ... 
doi:10.5281/zenodo.4088473 fatcat:qeargfvfbva4xkf32vmymiapoe

A Quantum Graph Neural Network Approach to Particle Track Reconstruction [article]

Cenk Tüysüz, Federico Carminati, Bilge Demirköz, Daniel Dobos, Fabio Fracas, Kristiane Novotny, Karolos Potamianos, Sofia Vallecorsa, Jean-Roch Vlimant
2020 arXiv   pre-print
In previous work, we have shown a first attempt of Quantum Computing to Graph Neural Networks for track reconstruction of particles.  ...  It has been demonstrated previously by HEP.TrkX using TrackML datasets, that graph neural networks, by processing events as a graph connecting track measurements can provide a promising solution by reducing  ...  This work was partially supported by Turkish Atomic Energy Authority (TAEK) (Grant No: 2017TAEKCERN-A5.H6.F2.15).  ... 
arXiv:2007.06868v1 fatcat:5fy65bhkjjbdrcdmdamgdxt4iy

Performance of a geometric deep learning pipeline for HL-LHC particle tracking

Xiangyang Ju, Daniel Murnane, Paolo Calafiura, Nicholas Choma, Sean Conlon, Steven Farrell, Yaoyuan Xu, Maria Spiropulu, Jean-Roch Vlimant, Adam Aurisano, Jeremy Hewes, Giuseppe Cerati (+12 others)
2021 European Physical Journal C: Particles and Fields  
The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity  ...  This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS  ...  Introduction Charged particle tracking plays an essential role in High-Energy Physics (HEP), including particle identification and kinematics, vertex finding, lepton reconstruction, and flavor jet tagging  ... 
doi:10.1140/epjc/s10052-021-09675-8 fatcat:vy3cu4tzknc7nkufcctfclz3oe

Track Seeding and Labelling with Embedded-space Graph Neural Networks [article]

Nicholas Choma, Daniel Murnane, Xiangyang Ju, Paolo Calafiura, Sean Conlon, Steven Farrell, Prabhat, Giuseppe Cerati, Lindsey Gray, Thomas Klijnsma, Jim Kowalkowski, Panagiotis Spentzouris (+7 others)
2020 arXiv   pre-print
Finally, we present numerical results on the TrackML particle tracking challenge dataset, where our framework shows favorable results in both seeding and track finding.  ...  To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction.  ...  Introduction High energy physics (HEP) experiments are designed to solve some of the most fundamental questions in the universe by probing the interactions of elementary particles in vast quantities of  ... 
arXiv:2007.00149v1 fatcat:n2amxcym4rginarfv7r4epf5cq

Charged particle tracking via edge-classifying interaction networks [article]

Gage DeZoort, Savannah Thais, Javier Duarte, Vesal Razavimaleki, Markus Atkinson, Isobel Ojalvo, Mark Neubauer, Peter Elmer
2021 arXiv   pre-print
Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high energy particle physics.  ...  In this work, we adapt the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider  ...  variety of tasks in high energy physics [26, 27] .  ... 
arXiv:2103.16701v3 fatcat:oxyiqvl2trehpomftgfn2672w4

CTD2020: Graph Neural Networks for Track Finding

Daniel Murnane
2020 Zenodo  
These feed into a high-accuracy N-plet classifier, a track parameter regression GNN, or can be used as an end-to-end track classifier by clustering in an embedded space.  ...  To address the unprecedented scale of HL-LHC data, the Exa.TrkX (previously HEP.TrkX) project has been investigating a variety of machine learning approaches to particle track reconstruction.  ...  Introduction High energy physics (HEP) experiments are designed to solve some of the most fundamental questions in the universe by probing the interactions of elementary particles in vast quantities of  ... 
doi:10.5281/zenodo.4088460 fatcat:5qzdpyuvkfau7chjcxza3rpkgm

Acts: A common tracking software [article]

Xiaocong Ai
2019 arXiv   pre-print
a much more challenging tracking environment.  ...  The reconstruction of charged particle trajectories is one of the most complex and CPU consuming parts of event processing in high energy experiments.  ...  Introduction The record-breaking data taking of the LHC in the second run (Run-2) between 2015 and 2018 provides chance for extraordinary exploration of the high-energy frontier.  ... 
arXiv:1910.03128v2 fatcat:kibqeggb35bibj675jwfmtuegu
« Previous Showing results 1 — 15 out of 53 results