{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T11:45:45Z","timestamp":1767008745615,"version":"3.37.3"},"reference-count":97,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T00:00:00Z","timestamp":1619136000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T00:00:00Z","timestamp":1619136000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolve this confrontation provided that algorithms can be sufficiently accelerated. In many cases, algorithmic speedups are found to be largest through the adoption of deep learning algorithms. We present a comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics. We present several realistic examples and discuss a strategy for the seamless integration of coprocessors so that the LHC can maintain, if not exceed, its current performance throughout its running.<\/jats:p>","DOI":"10.1088\/2632-2153\/abec21","type":"journal-article","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T22:31:37Z","timestamp":1614897097000},"page":"035005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["GPU coprocessors as a service for deep learning inference in high energy physics"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0785-7552","authenticated-orcid":false,"given":"Jeffrey","family":"Krupa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1494-1464","authenticated-orcid":false,"given":"Kelvin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5602-4704","authenticated-orcid":false,"given":"Maria","family":"Acosta Flechas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6401-778X","authenticated-orcid":false,"given":"Jack","family":"Dinsmore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5076-7096","authenticated-orcid":false,"given":"Javier","family":"Duarte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8189-3741","authenticated-orcid":false,"given":"Philip","family":"Harris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9516-0311","authenticated-orcid":false,"given":"Scott","family":"Hauck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5235-6314","authenticated-orcid":false,"given":"Burt","family":"Holzman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6214-8500","authenticated-orcid":false,"given":"Shih-Chieh","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1675-6040","authenticated-orcid":false,"given":"Thomas","family":"Klijnsma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-9151","authenticated-orcid":false,"given":"Kevin","family":"Pedro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8411-9620","authenticated-orcid":false,"given":"Dylan","family":"Rankin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natchanon","family":"Suaysom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9884-2326","authenticated-orcid":false,"given":"Matt","family":"Trahms","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8440-6854","authenticated-orcid":false,"given":"Nhan","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2021,4,23]]},"reference":[{"key":"mlstabec21bib1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/3\/08\/S08001","volume":"3","author":"Evans","year":"2008","journal-title":"J. Instrum."},{"article-title":"LHC Run-2 and future prospects","year":"2020","author":"Boyd","key":"mlstabec21bib2"},{"article-title":"LHC highlights and prospects","year":"2019","author":"Gerber","key":"mlstabec21bib3"},{"year":"2019","author":"","key":"mlstabec21bib4","doi-asserted-by":"publisher","DOI":"10.23731\/CYRM-2019-007"},{"key":"mlstabec21bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6471\/ab4574","article-title":"Searching for long-lived particles beyond the standard model at the large Hadron collider","volume":"47","author":"Alimena","year":"2020","journal-title":"J. Phys. G"},{"key":"mlstabec21bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dark.2019.100371","article-title":"Dark matter benchmark models for early LHC Run-2 searches: report of the ATLAS\/CMS dark matter forum","volume":"27","author":"Abercrombie","year":"2020","journal-title":"Phys. Dark Universe"},{"key":"mlstabec21bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physletb.2012.08.020","article-title":"Observation of a new particle in the search for the standard model Higgs boson with the ATLAS detector at the LHC","volume":"716","author":"","year":"2012","journal-title":"Phys. Lett. B"},{"key":"mlstabec21bib8","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.physletb.2012.08.021","article-title":"Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC","volume":"716","author":"","year":"2012","journal-title":"Phys. Lett. B"},{"key":"mlstabec21bib9","doi-asserted-by":"publisher","first-page":"081","DOI":"10.1007\/JHEP06(2013)081","article-title":"Observation of a new boson with mass near 125 GeV in pp collisions at s = 7 and 8 TeV","volume":"06","author":"","year":"2013","journal-title":"J. High Energy Phys."},{"key":"mlstabec21bib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.97.092005","article-title":"Search for new physics in final states with an energetic jet or a hadronically decaying W or Z boson and transverse momentum imbalance at s=13\u2009TeV","volume":"97","author":"","year":"2018","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib11","doi-asserted-by":"publisher","first-page":"033","DOI":"10.1007\/JHEP05(2020)033","article-title":"Search for high mass dijet resonances with a new background prediction method in proton\u2013proton collisions at s=13 TeV","volume":"05","author":"","year":"2020","journal-title":"J. High Energy Phys."},{"key":"mlstabec21bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.100.112007","article-title":"Search for low mass vector resonances decaying into quark-antiquark pairs in proton\u2013proton collisions at s= 13 TeV","volume":"100","author":"","year":"2019","journal-title":"Phys. Rev. D"},{"article-title":"Dark sectors 2016 workshop: community report","year":"2016","author":"Alexander","key":"mlstabec21bib13"},{"key":"mlstabec21bib14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1103\/PhysRevD.100.112007","article-title":"A roadmap for HEP software and computing R&D for the 2020s","volume":"3","author":"","year":"2019","journal-title":"Comput. Softw. Big Sci."},{"article-title":"CMS offline and computing public results","year":"2020","author":"","key":"mlstabec21bib15"},{"article-title":"ATLAS computing and software public results","year":"2020","author":"","key":"mlstabec21bib16"},{"year":"2017","author":"","key":"mlstabec21bib17"},{"key":"mlstabec21bib18","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1109\/JSSC.1974.1050511","article-title":"Design of ion-implanted MOSFET\u2019s with very small physical dimensions","volume":"9","author":"Dennard","year":"1974","journal-title":"IEEE J. Solid-State Circuits"},{"key":"mlstabec21bib19","doi-asserted-by":"publisher","first-page":"p 365","DOI":"10.1145\/2000064.2000108","article-title":"Dark silicon and the end of multicore scaling","author":"Esmaeilzadeh","year":"2011"},{"key":"mlstabec21bib20","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s41781-019-0027-2","article-title":"FPGA-accelerated machine learning inference as a service for particle physics computing","volume":"3","author":"Duarte","year":"2019","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstabec21bib21","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1146\/annurev-nucl-101917-021019","article-title":"Deep learning and its application to LHC physics","volume":"68","author":"Guest","year":"2018","journal-title":"Annu. Rev. Nucl. Part. Sci."},{"key":"mlstabec21bib22","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.1088\/1742-6596\/1085\/2\/022008","article-title":"Machine Learning in High Energy Physics Community White Paper","volume":"1085","author":"Albertsson","year":"022008","journal-title":"J. Phys. Conf. Ser."},{"key":"mlstabec21bib23","doi-asserted-by":"publisher","DOI":"10.1142\/S0217751X19300199","article-title":"Machine and deep learning applications in particle physics","volume":"34","author":"Bourilkov","year":"2020","journal-title":"Int. J. Mod. Phys. A"},{"key":"mlstabec21bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2019.11.001","article-title":"Jet substructure at the large Hadron collider: a review of recent advances in theory and machine learning","volume":"841","author":"Larkoski","year":"2020","journal-title":"Phys. Rep."},{"key":"mlstabec21bib25","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1140\/epjc\/s10052-019-7113-9","article-title":"Learning representations of irregular particle-detector geometry with distance-weighted graph networks","volume":"79","author":"Qasim","year":"2019","journal-title":"Eur. Phys. J. C"},{"key":"mlstabec21bib26","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1140\/epjc\/s10052-020-8251-9","article-title":"Calorimetry with deep learning: particle simulation and reconstruction for collider physics","volume":"80","author":"Belayneh","year":"2020","journal-title":"Eur. Phys. J. C"},{"key":"mlstabec21bib27","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/JHEP01(2017)110","article-title":"Deep learning in color: towards automated quark\/gluon jet discrimination","volume":"01","author":"Komiske","year":"2017","journal-title":"J. High Energy Phys."},{"article-title":"Quark versus gluon jet tagging using jet images with the ATLAS detector","year":"2017","author":"","key":"mlstabec21bib28"},{"key":"mlstabec21bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2020.164304","article-title":"End-to-end jet classification of quarks and gluons with the CMS Open Data","volume":"977","author":"Andrews","year":"2020","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"year":"2019","author":"","key":"mlstabec21bib30"},{"key":"mlstabec21bib31","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.SP.800-145","article-title":"The NIST definition of cloud computing","author":"Mell","year":"2011"},{"key":"mlstabec21bib32","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1085\/4\/042014","article-title":"GooFit 2.0","volume":"1085","author":"Schreiner","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"year":"2020","author":"Heinrich","key":"mlstabec21bib33"},{"article-title":"Processing columnar collider data with GPU-accelerated kernels","year":"2019","author":"Pata","key":"mlstabec21bib34"},{"key":"mlstabec21bib35","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.cpc.2019.04.011","article-title":"Real-time data processing in the ALICE high level trigger at the LHC","volume":"242","author":"","year":"2019","journal-title":"Comput. Phys. Commun."},{"key":"mlstabec21bib36","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s41781-020-00039-7","article-title":"Allen: a high level trigger on GPUs for LHCb","volume":"4","author":"Aaij","year":"2020","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstabec21bib37","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/06\/C06010","article-title":"Real-time data processing with GPUs in high energy physics","volume":"15","author":"Vom Bruch","year":"2020","journal-title":"J. Instrum."},{"key":"mlstabec21bib38","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3389\/fdata.2020.601728","article-title":"Heterogeneous reconstruction of tracks and primary vertices with the CMS pixel tracker","volume":"3","author":"Bocci","year":"2020","journal-title":"Front. Big Data"},{"key":"mlstabec21bib39","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/513\/5\/052010","article-title":"Parallel track reconstruction in CMS using the cellular automaton approach","volume":"513","author":"Funke","year":"2014","journal-title":"J. Phys. Conf. Ser."},{"key":"mlstabec21bib40","doi-asserted-by":"publisher","DOI":"10.1109\/NSSMIC.2015.7581775","article-title":"Development of a phase-II track trigger based on GPUs for the CMS experiment","author":"Pantaleo","year":"2016"},{"key":"mlstabec21bib41","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.nima.2014.05.073","article-title":"Almagest, a new trackless ring finding algorithm","volume":"766","author":"Lamanna","year":"2014","journal-title":"Nucl. Instr. Methods Phys. Res. A"},{"key":"mlstabec21bib42","doi-asserted-by":"publisher","first-page":"1994","DOI":"10.1109\/TNS.2017.2715900","article-title":"Particle identification on an FPGA accelerated compute platform for the LHCb upgrade","volume":"64","author":"F\u00e4erber","year":"2017","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"mlstabec21bib43","doi-asserted-by":"publisher","DOI":"10.1051\/epjconf\/201715000013","article-title":"Online data reduction using track and vertex reconstruction on GPUs for the Mu3e experiment","volume":"150","author":"","year":"2017","journal-title":"Eur. Phys. J. Conf."},{"key":"mlstabec21bib44","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1085\/3\/032022","article-title":"Real-time heterogeneous stream processing with NaNet in the NA62 experiment","volume":"1085","author":"Ammendola","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"mlstabec21bib45","doi-asserted-by":"publisher","first-page":"p 388","DOI":"10.1109\/eScience.2019.00050","article-title":"Photon propagation using GPUs by the IceCube neutrino observatory","author":"Chirkin","year":"2019"},{"key":"mlstabec21bib46","doi-asserted-by":"publisher","first-page":"p 23","DOI":"10.1007\/978-3-030-50743-5_2","author":"Sfiligoi","year":"2020"},{"year":"2020","author":"Pedro","key":"mlstabec21bib47"},{"key":"mlstabec21bib48","doi-asserted-by":"publisher","first-page":"p 1","DOI":"10.1109\/MICRO.2016.7783710","article-title":"A cloud-scale acceleration architecture","author":"Caulfield","year":"2016"},{"article-title":"Technical design report for the upgrade of the online-offline computing system","year":"2015","author":"","key":"mlstabec21bib49"},{"year":"2019","author":"","key":"mlstabec21bib50"},{"year":"2018","author":"","key":"mlstabec21bib51"},{"article-title":"CMS physics: technical design report volume 1: detector performance and software","year":"2006","author":"","key":"mlstabec21bib52"},{"year":"2018","author":"","key":"mlstabec21bib53"},{"key":"mlstabec21bib54","doi-asserted-by":"publisher","DOI":"10.1051\/epjconf\/202024505009","article-title":"Bringing heterogeneity to the CMS software framework","volume":"245","author":"Bocci","year":"2020","journal-title":"EPJ Conf."},{"key":"mlstabec21bib55","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3389\/fdata.2020.591315","article-title":"CLUE: a fast parallel clustering algorithm for high granularity calorimeters in high energy physics","volume":"3","author":"Rovere","year":"2020","journal-title":"Front. Big Data"},{"key":"mlstabec21bib56","first-page":"p 448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","volume":"vol 37","author":"Ioffe","year":"2015"},{"key":"mlstabec21bib57","first-page":"p 807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"Nair","year":"2010"},{"key":"mlstabec21bib58","first-page":"p 315","article-title":"Deep sparse rectifier neural networks","volume":"vol 15","author":"Glorot","year":"2011"},{"article-title":"Adam: a method for stochastic optimization","year":"2015","author":"Kingma","key":"mlstabec21bib59"},{"key":"mlstabec21bib60","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1162\/1\/012036","article-title":"New method of out-of-time energy subtraction for the CMS hadronic calorimeter","volume":"1162","author":"Lawhorn","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"mlstabec21bib61","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1525\/1\/012040","article-title":"Heterogeneous computing for the local reconstruction algorithms of the CMS calorimeters","volume":"1525","author":"Massironi","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"article-title":"Energy reconstruction of electrons and photons using convolutional neural networks","year":"2019","author":"Faye","key":"mlstabec21bib62"},{"key":"mlstabec21bib63","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/14\/03\/P03017","article-title":"Electron and photon energy calibration with the ATLAS detector using 2015\u20132016 LHC proton-proton collision data","volume":"14","author":"","year":"2019","journal-title":"J. Instrum."},{"key":"mlstabec21bib64","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/14\/12\/P12006","article-title":"Electron and photon performance measurements with the ATLAS detector using the 2015\u20132017 LHC proton-proton collision data","volume":"14","author":"","year":"2019","journal-title":"J. Instrum."},{"article-title":"Rectifier nonlinearities improve neural network acoustic models","year":"2013","author":"Maas","key":"mlstabec21bib65"},{"key":"mlstabec21bib66","doi-asserted-by":"publisher","first-page":"p 770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstabec21bib67","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/06\/P06005","article-title":"Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques","volume":"15","author":"","year":"2020","journal-title":"J. Instrum."},{"key":"mlstabec21bib68","doi-asserted-by":"publisher","first-page":"014","DOI":"10.21468\/SciPostPhys.7.1.014","article-title":"The machine learning landscape of top taggers","volume":"7","author":"Butter","year":"2019","journal-title":"SciPost Phys."},{"key":"mlstabec21bib69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41781-017-0001-9","article-title":"HEPCloud, a new paradigm for HEP facilities: CMS amazon web services investigation","volume":"1","author":"Holzman","year":"2017","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstabec21bib70","doi-asserted-by":"publisher","first-page":"p 352","DOI":"10.1109\/CCGRID.2018.00053","article-title":"Intelligently-automated facilities expansion with the HEPCloud decision engine","author":"Altunay","year":"2018"},{"key":"mlstabec21bib71","doi-asserted-by":"publisher","DOI":"10.1051\/epjconf\/201921403060","article-title":"HEPCloud, an elastic hybrid HEP facility using an intelligent decision support system","volume":"214","author":"Mhashilkar","year":"2019","journal-title":"Eur. Phys. J. Conf."},{"year":"2020","author":"","key":"mlstabec21bib72"},{"year":"2020","author":"","key":"mlstabec21bib73"},{"year":"2020","author":"","key":"mlstabec21bib74"},{"year":"2020","author":"","key":"mlstabec21bib75"},{"key":"mlstabec21bib76","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/664\/8\/082044","article-title":"Performance of the CMS High Level Trigger","volume":"664","author":"Perrotta","year":"2015","journal-title":"J. Phys. Conf. Ser."},{"key":"mlstabec21bib77","doi-asserted-by":"publisher","DOI":"10.1051\/epjconf\/201818202037","article-title":"CMS trigger performance","volume":"182","author":"","year":"2018","journal-title":"Eur. Phys. J. Conf."},{"key":"mlstabec21bib78","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.056019","article-title":"ParticleNet: jet tagging via particle clouds","volume":"101","author":"Qu","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib79","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1140\/epjc\/s10052-018-6144-y","article-title":"Measurement of charged particle spectra in minimum-bias events from proton\u2013proton collisions at s=13TeV","volume":"78","author":"","year":"2018","journal-title":"Eur. Phys. J. C"},{"key":"mlstabec21bib80","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab9023","article-title":"A deep neural network to search for new long-lived particles decaying to jets","volume":"1","author":"","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstabec21bib81","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/JHEP10(2017)174","article-title":"Classification without labels: learning from mixed samples in high energy physics","volume":"10","author":"Metodiev","year":"2017","journal-title":"J. High Energy Phys."},{"key":"mlstabec21bib82","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.075042","article-title":"Anomaly detection with density estimation","volume":"101","author":"Nachman","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib83","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.095004","article-title":"Simulation assisted likelihood-free anomaly detection","volume":"101","author":"Andreassen","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib84","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.241803","article-title":"Anomaly detection for resonant new physics with machine learning","volume":"121","author":"Collins","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstabec21bib85","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.99.014038","article-title":"Extending the search for new resonances with machine learning","volume":"99","author":"Collins","year":"2019","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib86","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.075021","article-title":"Searching for new physics with deep autoencoders","volume":"101","author":"Farina","year":"2020","journal-title":"Phys. Rev. D"},{"key":"mlstabec21bib87","doi-asserted-by":"publisher","first-page":"030","DOI":"10.21468\/SciPostPhys.6.3.030","article-title":"QCD or what?","volume":"6","author":"Heimel","year":"2019","journal-title":"SciPost Phys."},{"article-title":"Novel deep learning methods for track reconstruction","year":"2018","author":"Farrell","key":"mlstabec21bib88"},{"article-title":"Graph neural networks for particle reconstruction in high energy physics detectors","year":"2019","author":"Ju","key":"mlstabec21bib89"},{"key":"mlstabec21bib90","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1140\/epjc\/s10052-020-7608-4","article-title":"JEDI-net: a jet identification algorithm based on interaction networks","volume":"80","author":"Moreno","year":"2020","journal-title":"Eur. Phys. J. C"},{"key":"mlstabec21bib91","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.102.012010","article-title":"Interaction networks for the identification of boosted H\u2192bb\u203e decays","volume":"102","author":"Moreno","year":"2020","journal-title":"Phys. Rev. D"},{"article-title":"Track seeding and labelling with embedded-space graph neural networks","year":"2020","author":"Choma","key":"mlstabec21bib92"},{"article-title":"Lorentz group equivariant neural network for particle physics","year":"2020","author":"Bogatskiy","key":"mlstabec21bib93"},{"key":"mlstabec21bib94","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1140\/epjc\/s10052-020-08461-2","article-title":"Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data","volume":"80","author":"Kieseler","year":"2020","journal-title":"Eur. Phys. J. C"},{"key":"mlstabec21bib95","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1140\/epjp\/s13360-020-00497-3","article-title":"ABCNet: an attention-based method for particle tagging","volume":"135","author":"Mikuni","year":"2020","journal-title":"Eur. Phys. J. Plus"},{"key":"mlstabec21bib96","doi-asserted-by":"crossref","DOI":"10.1140\/epjc\/s10052-021-09158-w","article-title":"MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks","author":"Pata","year":"2021"},{"key":"mlstabec21bib97","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3389\/fdata.2020.604083","article-title":"GPU-accelerated machine learning inference as a service for computing in neutrino experiments","volume":"3","author":"Wang","year":"2020","journal-title":"Front. Big Data"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T16:28:38Z","timestamp":1641918518000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abec21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,23]]},"references-count":97,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,4,23]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abec21","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2021,4,23]]},"assertion":[{"value":"GPU coprocessors as a service for deep learning inference in high energy physics","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-07-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-03-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}