Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment
Descripción del Articulo
Construction support also was granted by the United States National Science Foundation under Award PHY-0619727 and by the University of Rochester. Additional support for participating scientists was provided by NSF and DOE (U.S.A.) by CAPES and CNPq (Brazil), by CoNaCyT (Mexico), by Proyecto Basal F...
| Autores: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | artículo |
| Fecha de Publicación: | 2018 |
| Institución: | Consejo Nacional de Ciencia Tecnología e Innovación |
| Repositorio: | CONCYTEC-Institucional |
| Lenguaje: | inglés |
| OAI Identifier: | oai:repositorio.concytec.gob.pe:20.500.12390/587 |
| Enlace del recurso: | https://hdl.handle.net/20.500.12390/587 https://doi.org/10.1088/1748-0221/13/11/P11020 |
| Nivel de acceso: | acceso abierto |
| Materia: | Physics programs Neural networks Neutrons Pattern recognition Deep convolutional neural networks Learning classifiers Learning-based methods Neutrino detectors Neutrino interactions Performance degradation https://purl.org/pe-repo/ocde/ford#3.01.00 |
| id |
CONC_b602fbbb178af9f0fdc133aac690813b |
|---|---|
| oai_identifier_str |
oai:repositorio.concytec.gob.pe:20.500.12390/587 |
| network_acronym_str |
CONC |
| network_name_str |
CONCYTEC-Institucional |
| repository_id_str |
4689 |
| dc.title.none.fl_str_mv |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| title |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| spellingShingle |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment Nuruzzaman Physics programs Neural networks Neutrons Pattern recognition Deep convolutional neural networks Learning classifiers Learning-based methods Neutrino detectors Neutrino interactions Performance degradation https://purl.org/pe-repo/ocde/ford#3.01.00 |
| title_short |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| title_full |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| title_fullStr |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| title_full_unstemmed |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| title_sort |
Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment |
| author |
Nuruzzaman |
| author_facet |
Nuruzzaman Perdue G.N. Ghosh A. Wospakrik M. Akbar F. Andrade D.A. Ascencio M. Bellantoni L. Bercellie A. Betancourt M. Vera G.F.R.C. Cai T. Carneiro M.F. Chaves J. Coplowe D. Motta H.D. Díaz G.A. Felix J. Fields L. Fine R. Gago A.M. Galindo R. Golan T. Gran R. Han J.Y. Harris D.A. Jena D. Kleykamp J. Kordosky M. Lu X.-G. Maher E. Mann W.A. Marshall C.M. McFarland K.S. McGowan A.M. Messerly B. Miller J. Nelson J.K. Nguyen C. Norrick A. Nuruzzaman N. Olivier A. Patton R. Ramírez M.A. Ransome R.D. Ray H. Ren L. Rimal D. Ruterbories D. Schellman H. Salinas C.J.S. Su H. Upadhyay S. Valencia E. Wolcott J. Yaeggy B. Young S. |
| author_role |
author |
| author2 |
Perdue G.N. Ghosh A. Wospakrik M. Akbar F. Andrade D.A. Ascencio M. Bellantoni L. Bercellie A. Betancourt M. Vera G.F.R.C. Cai T. Carneiro M.F. Chaves J. Coplowe D. Motta H.D. Díaz G.A. Felix J. Fields L. Fine R. Gago A.M. Galindo R. Golan T. Gran R. Han J.Y. Harris D.A. Jena D. Kleykamp J. Kordosky M. Lu X.-G. Maher E. Mann W.A. Marshall C.M. McFarland K.S. McGowan A.M. Messerly B. Miller J. Nelson J.K. Nguyen C. Norrick A. Nuruzzaman N. Olivier A. Patton R. Ramírez M.A. Ransome R.D. Ray H. Ren L. Rimal D. Ruterbories D. Schellman H. Salinas C.J.S. Su H. Upadhyay S. Valencia E. Wolcott J. Yaeggy B. Young S. |
| author2_role |
author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author author |
| dc.contributor.author.fl_str_mv |
Nuruzzaman Perdue G.N. Ghosh A. Wospakrik M. Akbar F. Andrade D.A. Ascencio M. Bellantoni L. Bercellie A. Betancourt M. Vera G.F.R.C. Cai T. Carneiro M.F. Chaves J. Coplowe D. Motta H.D. Díaz G.A. Felix J. Fields L. Fine R. Gago A.M. Galindo R. Golan T. Gran R. Han J.Y. Harris D.A. Jena D. Kleykamp J. Kordosky M. Lu X.-G. Maher E. Mann W.A. Marshall C.M. McFarland K.S. McGowan A.M. Messerly B. Miller J. Nelson J.K. Nguyen C. Norrick A. Nuruzzaman N. Olivier A. Patton R. Ramírez M.A. Ransome R.D. Ray H. Ren L. Rimal D. Ruterbories D. Schellman H. Salinas C.J.S. Su H. Upadhyay S. Valencia E. Wolcott J. Yaeggy B. Young S. |
| dc.subject.none.fl_str_mv |
Physics programs |
| topic |
Physics programs Neural networks Neutrons Pattern recognition Deep convolutional neural networks Learning classifiers Learning-based methods Neutrino detectors Neutrino interactions Performance degradation https://purl.org/pe-repo/ocde/ford#3.01.00 |
| dc.subject.es_PE.fl_str_mv |
Neural networks Neutrons Pattern recognition Deep convolutional neural networks Learning classifiers Learning-based methods Neutrino detectors Neutrino interactions Performance degradation |
| dc.subject.ocde.none.fl_str_mv |
https://purl.org/pe-repo/ocde/ford#3.01.00 |
| description |
Construction support also was granted by the United States National Science Foundation under Award PHY-0619727 and by the University of Rochester. Additional support for participating scientists was provided by NSF and DOE (U.S.A.) by CAPES and CNPq (Brazil), by CoNaCyT (Mexico), by Proyecto Basal FB 0821, CONICYT PIA ACT1413, Fondecyt 3170845 and 11130133 (Chile), by PIIC (DGIP-UTFSM), by CONCYTEC, DGI-PUCP and IDI/IGI-UNI (Peru) |
| publishDate |
2018 |
| dc.date.accessioned.none.fl_str_mv |
2024-05-30T23:13:38Z |
| dc.date.available.none.fl_str_mv |
2024-05-30T23:13:38Z |
| dc.date.issued.fl_str_mv |
2018 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/article |
| format |
article |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12390/587 |
| dc.identifier.doi.none.fl_str_mv |
https://doi.org/10.1088/1748-0221/13/11/P11020 |
| dc.identifier.scopus.none.fl_str_mv |
2-s2.0-85057619219 |
| url |
https://hdl.handle.net/20.500.12390/587 https://doi.org/10.1088/1748-0221/13/11/P11020 |
| identifier_str_mv |
2-s2.0-85057619219 |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.ispartof.none.fl_str_mv |
Journal of Instrumentation |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| eu_rights_str_mv |
openAccess |
| dc.publisher.none.fl_str_mv |
Institute of Physics Publishing |
| publisher.none.fl_str_mv |
Institute of Physics Publishing |
| dc.source.none.fl_str_mv |
reponame:CONCYTEC-Institucional instname:Consejo Nacional de Ciencia Tecnología e Innovación instacron:CONCYTEC |
| instname_str |
Consejo Nacional de Ciencia Tecnología e Innovación |
| instacron_str |
CONCYTEC |
| institution |
CONCYTEC |
| reponame_str |
CONCYTEC-Institucional |
| collection |
CONCYTEC-Institucional |
| repository.name.fl_str_mv |
Repositorio Institucional CONCYTEC |
| repository.mail.fl_str_mv |
repositorio@concytec.gob.pe |
| _version_ |
1844883058951454720 |
| spelling |
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 G.N.Ghosh A.Wospakrik M.Akbar F.Andrade D.A.Ascencio M.Bellantoni L.Bercellie A.Betancourt M.Vera G.F.R.C.Cai T.Carneiro M.F.Chaves J.Coplowe D.Motta H.D.Díaz G.A.Felix J.Fields L.Fine R.Gago A.M.Galindo R.Golan T.Gran R.Han J.Y.Harris D.A.Jena D.Kleykamp J.Kordosky M.Lu X.-G.Maher E.Mann W.A.Marshall C.M.McFarland K.S.McGowan A.M.Messerly B.Miller J.Nelson J.K.Nguyen C.Norrick A.Nuruzzaman N.Olivier A.Patton R.Ramírez M.A.Ransome R.D.Ray H.Ren L.Rimal D.Ruterbories D.Schellman H.Salinas C.J.S.Su H.Upadhyay S.Valencia E.Wolcott J.Yaeggy B.Young S.2024-05-30T23:13:38Z2024-05-30T23:13:38Z2018https://hdl.handle.net/20.500.12390/587https://doi.org/10.1088/1748-0221/13/11/P110202-s2.0-85057619219Construction support also was granted by the United States National Science Foundation under Award PHY-0619727 and by the University of Rochester. Additional support for participating scientists was provided by NSF and DOE (U.S.A.) by CAPES and CNPq (Brazil), by CoNaCyT (Mexico), by Proyecto Basal FB 0821, CONICYT PIA ACT1413, Fondecyt 3170845 and 11130133 (Chile), by PIIC (DGIP-UTFSM), by CONCYTEC, DGI-PUCP and IDI/IGI-UNI (Peru)We present a simulation-based study using deep convolutional neural networks (DCNNs) to identify neutrino interaction vertices in the MINERvA passive targets region, and illustrate the application of domain adversarial neural networks (DANNs) in this context. DANNs are designed to be trained in one domain (simulated data) but tested in a second domain (physics data) and utilize unlabeled data from the second domain so that during training only features which are unable to discriminate between the domains are promoted. MINERvA is a neutrino-nucleus scattering experiment using the NuMI beamline at Fermilab. A-dependent cross sections are an important part of the physics program, and these measurements require vertex finding in complicated events. To illustrate the impact of the DANN we used a modified set of simulation in place of physics data during the training of the DANN and then used the label of the modified simulation during the evaluation of the DANN. We find that deep learning based methods offer significant advantages over our prior track-based reconstruction for the task of vertex finding, and that DANNs are able to improve the performance of deep networks by leveraging available unlabeled data and by mitigating network performance degradation rooted in biases in the physics models used for training.Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - ConcytecengInstitute of Physics PublishingJournal of Instrumentationinfo:eu-repo/semantics/openAccessPhysics programsNeural networks-1Neutrons-1Pattern recognition-1Deep convolutional neural networks-1Learning classifiers-1Learning-based methods-1Neutrino detectors-1Neutrino interactions-1Performance degradation-1https://purl.org/pe-repo/ocde/ford#3.01.00-1Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experimentinfo:eu-repo/semantics/articlereponame:CONCYTEC-Institucionalinstname:Consejo Nacional de Ciencia Tecnología e Innovacióninstacron:CONCYTEC20.500.12390/587oai:repositorio.concytec.gob.pe:20.500.12390/5872024-05-30 15:58:08.405http://purl.org/coar/access_right/c_14cbinfo:eu-repo/semantics/closedAccessmetadata only accesshttps://repositorio.concytec.gob.peRepositorio Institucional CONCYTECrepositorio@concytec.gob.pe#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1a36c8cf-0855-409e-8538-920fc2aaf966"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment</Title> <PublishedIn> <Publication> <Title>Journal of Instrumentation</Title> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <DOI>https://doi.org/10.1088/1748-0221/13/11/P11020</DOI> <SCP-Number>2-s2.0-85057619219</SCP-Number> <Authors> <Author> <DisplayName>Nuruzzaman</DisplayName> <Person id="rp00755" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Perdue G.N.</DisplayName> <Person id="rp00806" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ghosh A.</DisplayName> <Person id="rp00787" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Wospakrik M.</DisplayName> <Person id="rp00782" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Akbar F.</DisplayName> <Person id="rp00805" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Andrade D.A.</DisplayName> <Person id="rp00803" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ascencio M.</DisplayName> <Person id="rp01138" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Bellantoni L.</DisplayName> <Person id="rp00818" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Bercellie A.</DisplayName> <Person id="rp00801" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Betancourt M.</DisplayName> <Person id="rp00807" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Vera G.F.R.C.</DisplayName> <Person id="rp00792" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Cai T.</DisplayName> <Person id="rp00756" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Carneiro M.F.</DisplayName> <Person id="rp00761" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Chaves J.</DisplayName> <Person id="rp01133" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Coplowe D.</DisplayName> <Person id="rp00785" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Motta H.D.</DisplayName> <Person id="rp01139" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Díaz G.A.</DisplayName> <Person id="rp00797" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Felix J.</DisplayName> <Person id="rp00774" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Fields L.</DisplayName> <Person id="rp00791" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Fine R.</DisplayName> <Person id="rp00813" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Gago A.M.</DisplayName> <Person id="rp00854" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Galindo R.</DisplayName> <Person id="rp01060" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Golan T.</DisplayName> <Person id="rp01057" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Gran R.</DisplayName> <Person id="rp00784" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Han J.Y.</DisplayName> <Person id="rp00753" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Harris D.A.</DisplayName> <Person id="rp00775" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Jena D.</DisplayName> <Person id="rp00777" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Kleykamp J.</DisplayName> <Person id="rp00815" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Kordosky M.</DisplayName> <Person id="rp00794" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Lu X.-G.</DisplayName> <Person id="rp00798" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Maher E.</DisplayName> <Person id="rp00783" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Mann W.A.</DisplayName> <Person id="rp00814" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Marshall C.M.</DisplayName> <Person id="rp00786" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>McFarland K.S.</DisplayName> <Person id="rp00779" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>McGowan A.M.</DisplayName> <Person id="rp00817" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Messerly B.</DisplayName> <Person id="rp00793" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Miller J.</DisplayName> <Person id="rp00768" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Nelson J.K.</DisplayName> <Person id="rp00780" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Nguyen C.</DisplayName> <Person id="rp00788" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Norrick A.</DisplayName> <Person id="rp00754" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Nuruzzaman N.</DisplayName> <Person id="rp01136" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Olivier A.</DisplayName> <Person id="rp00767" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Patton R.</DisplayName> <Person id="rp01134" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ramírez M.A.</DisplayName> <Person id="rp00795" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ransome R.D.</DisplayName> <Person id="rp00802" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ray H.</DisplayName> <Person id="rp00766" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ren L.</DisplayName> <Person id="rp00763" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Rimal D.</DisplayName> <Person id="rp00804" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ruterbories D.</DisplayName> <Person id="rp00778" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Schellman H.</DisplayName> <Person id="rp00773" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Salinas C.J.S.</DisplayName> <Person id="rp00809" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Su H.</DisplayName> <Person id="rp00752" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Upadhyay S.</DisplayName> <Person id="rp01137" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Valencia E.</DisplayName> <Person id="rp00796" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Wolcott J.</DisplayName> <Person id="rp00822" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Yaeggy B.</DisplayName> <Person id="rp00816" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Young S.</DisplayName> <Person id="rp01135" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Institute of Physics Publishing</DisplayName> <OrgUnit /> </Publisher> </Publishers> <Keyword>Physics programs</Keyword> <Keyword>Neural networks</Keyword> <Keyword>Neutrons</Keyword> <Keyword>Pattern recognition</Keyword> <Keyword>Deep convolutional neural networks</Keyword> <Keyword>Learning classifiers</Keyword> <Keyword>Learning-based methods</Keyword> <Keyword>Neutrino detectors</Keyword> <Keyword>Neutrino interactions</Keyword> <Keyword>Performance degradation</Keyword> <Abstract>We present a simulation-based study using deep convolutional neural networks (DCNNs) to identify neutrino interaction vertices in the MINERvA passive targets region, and illustrate the application of domain adversarial neural networks (DANNs) in this context. DANNs are designed to be trained in one domain (simulated data) but tested in a second domain (physics data) and utilize unlabeled data from the second domain so that during training only features which are unable to discriminate between the domains are promoted. MINERvA is a neutrino-nucleus scattering experiment using the NuMI beamline at Fermilab. A-dependent cross sections are an important part of the physics program, and these measurements require vertex finding in complicated events. To illustrate the impact of the DANN we used a modified set of simulation in place of physics data during the training of the DANN and then used the label of the modified simulation during the evaluation of the DANN. We find that deep learning based methods offer significant advantages over our prior track-based reconstruction for the task of vertex finding, and that DANNs are able to improve the performance of deep networks by leveraging available unlabeled data and by mitigating network performance degradation rooted in biases in the physics models used for training.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication> -1 |
| score |
13.476704 |
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).
