Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification
Measurements in Liquid Argon Time Projection Chamber neutrino detectors feature large, high fidelity event images. Deep learning techniques have been extremely successful in classification tasks of photographs, but their application to these event images is challenging, due to the large size of the...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2019-01-01
|
Series: | EPJ Web of Conferences |
Online Access: | https://www.epj-conferences.org/articles/epjconf/pdf/2019/19/epjconf_chep2018_06016.pdf |
id |
doaj-3d1ab29c01764a58931ead37c64be78b |
---|---|
record_format |
Article |
spelling |
doaj-3d1ab29c01764a58931ead37c64be78b2021-08-02T09:05:10ZengEDP SciencesEPJ Web of Conferences2100-014X2019-01-012140601610.1051/epjconf/201921406016epjconf_chep2018_06016Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classificationStrube JanBhattacharya KolahalChurch EricDaily JeffMalachi SchramCharles SiegelKevin WiermanMeasurements in Liquid Argon Time Projection Chamber neutrino detectors feature large, high fidelity event images. Deep learning techniques have been extremely successful in classification tasks of photographs, but their application to these event images is challenging, due to the large size of the events, more two orders of magnitude larger than images found in classical challenges like MNIST or ImageNet. This leads to extremely long training cycles, which slow down the exploration of new network architectures and hyperpa-rameter scans to improve the classification performance. We present studies of scaling an LArTPC classification problem on multiple architectures, spanning multiple nodes. The studies are carried out in simulated events in the Micro-BooNE detector.https://www.epj-conferences.org/articles/epjconf/pdf/2019/19/epjconf_chep2018_06016.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Strube Jan Bhattacharya Kolahal Church Eric Daily Jeff Malachi Schram Charles Siegel Kevin Wierman |
spellingShingle |
Strube Jan Bhattacharya Kolahal Church Eric Daily Jeff Malachi Schram Charles Siegel Kevin Wierman Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification EPJ Web of Conferences |
author_facet |
Strube Jan Bhattacharya Kolahal Church Eric Daily Jeff Malachi Schram Charles Siegel Kevin Wierman |
author_sort |
Strube Jan |
title |
Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification |
title_short |
Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification |
title_full |
Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification |
title_fullStr |
Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification |
title_full_unstemmed |
Scaling studies for deep learning in Liquid Argon Time Projection Chamber event classification |
title_sort |
scaling studies for deep learning in liquid argon time projection chamber event classification |
publisher |
EDP Sciences |
series |
EPJ Web of Conferences |
issn |
2100-014X |
publishDate |
2019-01-01 |
description |
Measurements in Liquid Argon Time Projection Chamber neutrino detectors feature large, high fidelity event images. Deep learning techniques have been extremely successful in classification tasks of photographs, but their application to these event images is challenging, due to the large size of the events, more two orders of magnitude larger than images found in classical challenges like MNIST or ImageNet. This leads to extremely long training cycles, which slow down the exploration of new network architectures and hyperpa-rameter scans to improve the classification performance. We present studies of scaling an LArTPC classification problem on multiple architectures, spanning multiple nodes. The studies are carried out in simulated events in the Micro-BooNE detector. |
url |
https://www.epj-conferences.org/articles/epjconf/pdf/2019/19/epjconf_chep2018_06016.pdf |
work_keys_str_mv |
AT strubejan scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT bhattacharyakolahal scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT churcheric scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT dailyjeff scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT malachischram scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT charlessiegel scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification AT kevinwierman scalingstudiesfordeeplearninginliquidargontimeprojectionchambereventclassification |
_version_ |
1721236377813647360 |