Machine learning for surface prediction in ACTS

We present an ongoing R&D activity for machine-learning-assisted navigation through detectors to be used for track reconstruction. We investigate different approaches of training neural networks for surface prediction and compare their results. This work is carried out in the context of the ACTS...

Full description

Bibliographic Details
Main Authors: Huth Benjamin, Salzburger Andreas, Wettig Tilo
Format: Article
Language:English
Published: EDP Sciences 2021-01-01
Series:EPJ Web of Conferences
Online Access:https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03053.pdf
id doaj-c91287d672a8434f90f24509dc23196d
record_format Article
spelling doaj-c91287d672a8434f90f24509dc23196d2021-08-26T09:27:32ZengEDP SciencesEPJ Web of Conferences2100-014X2021-01-012510305310.1051/epjconf/202125103053epjconf_chep2021_03053Machine learning for surface prediction in ACTSHuth Benjamin0Salzburger Andreas1Wettig Tilo2Department of Physics, University of RegensburgCERNDepartment of Physics, University of RegensburgWe present an ongoing R&D activity for machine-learning-assisted navigation through detectors to be used for track reconstruction. We investigate different approaches of training neural networks for surface prediction and compare their results. This work is carried out in the context of the ACTS tracking toolkit.https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03053.pdf
collection DOAJ
language English
format Article
sources DOAJ
author Huth Benjamin
Salzburger Andreas
Wettig Tilo
spellingShingle Huth Benjamin
Salzburger Andreas
Wettig Tilo
Machine learning for surface prediction in ACTS
EPJ Web of Conferences
author_facet Huth Benjamin
Salzburger Andreas
Wettig Tilo
author_sort Huth Benjamin
title Machine learning for surface prediction in ACTS
title_short Machine learning for surface prediction in ACTS
title_full Machine learning for surface prediction in ACTS
title_fullStr Machine learning for surface prediction in ACTS
title_full_unstemmed Machine learning for surface prediction in ACTS
title_sort machine learning for surface prediction in acts
publisher EDP Sciences
series EPJ Web of Conferences
issn 2100-014X
publishDate 2021-01-01
description We present an ongoing R&D activity for machine-learning-assisted navigation through detectors to be used for track reconstruction. We investigate different approaches of training neural networks for surface prediction and compare their results. This work is carried out in the context of the ACTS tracking toolkit.
url https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03053.pdf
work_keys_str_mv AT huthbenjamin machinelearningforsurfacepredictioninacts
AT salzburgerandreas machinelearningforsurfacepredictioninacts
AT wettigtilo machinelearningforsurfacepredictioninacts
_version_ 1721195825109925888