{"id":"https://openalex.org/W2903731869","doi":"https://doi.org/10.1109/tmscs.2018.2886266","title":"Scalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic Streaming","display_name":"Scalable FPGA Accelerator for Deep Convolutional Neural Networks with Stochastic Streaming","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2903731869","doi":"https://doi.org/10.1109/tmscs.2018.2886266","mag":"2903731869"},"language":"en","primary_location":{"id":"doi:10.1109/tmscs.2018.2886266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmscs.2018.2886266","pdf_url":null,"source":{"id":"https://openalex.org/S4210201583","display_name":"IEEE Transactions on Multi-Scale Computing Systems","issn_l":"2332-7766","issn":["2332-7766","2372-207X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multi-Scale Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1493138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079607802","display_name":"Mohammed Alawad","orcid":"https://orcid.org/0000-0002-7491-0440"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Alawad","raw_affiliation_strings":["Health Data Sciences Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-7491-0440","affiliations":[{"raw_affiliation_string":"Health Data Sciences Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3225-4406","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7292,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.73705829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":"4","first_page":"888","last_page":"899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reconfigurability","display_name":"Reconfigurability","score":0.9560331106185913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8467973470687866},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8117902874946594},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7760857939720154},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6566511392593384},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5775823593139648},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5593481063842773},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4771430194377899},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4737573266029358},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4702654778957367},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4214564859867096},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.4130491316318512},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34686899185180664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2786824107170105}],"concepts":[{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.9560331106185913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467973470687866},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8117902874946594},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7760857939720154},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6566511392593384},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5775823593139648},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5593481063842773},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4771430194377899},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4737573266029358},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4702654778957367},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4214564859867096},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.4130491316318512},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34686899185180664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2786824107170105},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tmscs.2018.2886266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmscs.2018.2886266","pdf_url":null,"source":{"id":"https://openalex.org/S4210201583","display_name":"IEEE Transactions on Multi-Scale Computing Systems","issn_l":"2332-7766","issn":["2332-7766","2372-207X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multi-Scale Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1493138","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1493138","pdf_url":"https://www.osti.gov/servlets/purl/1493138","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:stars.library.ucf.edu:scopus2015-11403","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2015/10404","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2015-2019","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1493138","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1493138","pdf_url":"https://www.osti.gov/servlets/purl/1493138","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2411683797","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G258018648","display_name":null,"funder_award_id":"N16-22-6056","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3945850812","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5164495282","display_name":"SHF: Small: Bio-Inspired Logic Design with Graph and Field Theory","funder_award_id":"1319884","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5589556504","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6713583405","display_name":null,"funder_award_id":"ECCS-1342225","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7836212937","display_name":"BRIGE: Minimum-Energy Bio-Inspired Analogic Computing Devices with Stochastic Switching Transistors under Ultra-Low VDD","funder_award_id":"1342225","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320310161","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12"},{"id":"https://openalex.org/F4320334233","display_name":"Data Science Institute, Columbia University","ror":null},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903731869.pdf","grobid_xml":"https://content.openalex.org/works/W2903731869.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1665214252","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1903029394","https://openalex.org/W1990315422","https://openalex.org/W1999085092","https://openalex.org/W2009832130","https://openalex.org/W2015048865","https://openalex.org/W2028820173","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2096733369","https://openalex.org/W2125203716","https://openalex.org/W2152839228","https://openalex.org/W2163605009","https://openalex.org/W2173128195","https://openalex.org/W2251143283","https://openalex.org/W2252908030","https://openalex.org/W2276486856","https://openalex.org/W2278433511","https://openalex.org/W2288502450","https://openalex.org/W2495112539","https://openalex.org/W2498260651","https://openalex.org/W2516141709","https://openalex.org/W2516828042","https://openalex.org/W2520083297","https://openalex.org/W2529546376","https://openalex.org/W2583383421","https://openalex.org/W2584311934","https://openalex.org/W2608407169","https://openalex.org/W2611120904","https://openalex.org/W2751555667","https://openalex.org/W2764024122","https://openalex.org/W2789246071","https://openalex.org/W2964259192","https://openalex.org/W2964299589","https://openalex.org/W3004171485","https://openalex.org/W4302296459","https://openalex.org/W6626177569","https://openalex.org/W6637151318","https://openalex.org/W6637242042","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6685504925","https://openalex.org/W6691600824","https://openalex.org/W6694596856","https://openalex.org/W6745510850"],"related_works":["https://openalex.org/W2159103767","https://openalex.org/W3103981520","https://openalex.org/W200972441","https://openalex.org/W2038220260","https://openalex.org/W1857140530","https://openalex.org/W1545578515","https://openalex.org/W1612076744","https://openalex.org/W2150194641","https://openalex.org/W1544665014","https://openalex.org/W2098458348"],"abstract_inverted_index":{"FPGA-based":[0,26,60,194,228],"heterogeneous":[1],"computing":[2,17,70,127,155],"platform,":[3],"due":[4,38,188],"to":[5,11,39,90,111,149,189],"its":[6,68,172],"extreme":[7],"logic":[8,80],"reconfigurability,":[9,45],"emerges":[10],"be":[12],"a":[13,23,113,125,167,199],"strong":[14],"contender":[15],"as":[16],"fabric":[18],"in":[19,99],"modern":[20,34],"AI.":[21],"As":[22],"result,":[24],"various":[25],"accelerators":[27],"for":[28,120],"deep":[29,142,195,229],"CNN\u2014the":[30],"key":[31,108,138],"driver":[32],"of":[33,42,101,140,171,254],"AI\u2014have":[35],"been":[36],"proposed":[37,163,221],"their":[40],"advantages":[41],"high":[43],"performance,":[44],"and":[46,105,117,147,157,241],"fast":[47],"development":[48],"round,":[49],"etc.":[50],"In":[51,82],"general,":[52],"the":[53,177,211],"consensus":[54],"among":[55],"researchers":[56],"is":[57,110,258],"that,":[58],"although":[59],"accelerator":[61],"can":[62,174],"achieve":[63],"much":[64],"higher":[65],"energy":[66,158],"efficiency,":[67],"raw":[69],"performance":[71,134,156],"lags":[72],"behind":[73],"when":[74,203,245],"compared":[75,204,246],"with":[76,78,94,205,247,261],"GPUs":[77,98],"similar":[79],"density.":[81],"this":[83],"paper,":[84],"we":[85],"develop":[86],"an":[87],"alternative":[88],"methodology":[89],"efficiently":[91],"implement":[92],"CNNs":[93,122],"FPGAs":[95],"that":[96,123,219],"outperform":[97],"terms":[100],"both":[102],"power":[103],"consumption":[104],"performance.":[106],"Our":[107],"idea":[109],"design":[112,119],"scalable":[114],"hardware":[115,201],"architecture":[116,165,223],"circuit":[118],"large-scale":[121],"leverages":[124],"stochastic-based":[126],"principle.":[128],"Specifically,":[129],"there":[130],"are":[131,145],"three":[132],"major":[133],"advantages.":[135],"First,":[136],"all":[137,170,226],"components":[139],"our":[141,162,193,220],"learning":[143],"CNN":[144,164,196,222,230,249,257],"designed":[146],"implemented":[148],"compute":[150],"stochastically,":[151],"thus":[152],"achieving":[153],"excellent":[154],"efficiency.":[159],"Second,":[160],"because":[161],"enables":[166],"stream-mode":[168],"computing,":[169],"stages":[173],"process":[175],"even":[176],"partial":[178],"results":[179,217],"from":[180],"preceding":[181],"stages,":[182],"therefore":[183],"not":[184],"incurring":[185],"unnecessary":[186],"latency":[187],"data":[190],"dependency.":[191],"Finally,":[192],"also":[197],"provides":[198],"superior":[200],"scalability":[202],"conventional":[206],"FPGA":[207],"implementations":[208],"by":[209],"reducing":[210],"bandwidth":[212],"requirement":[213],"between":[214],"layers.":[215],"The":[216,251],"show":[218],"significantly":[224],"outperforms":[225],"previous":[227],"implementation":[231],"approaches.":[232],"It":[233],"achieves":[234],"1.58x":[235],"more":[236,239,243],"GOPS,":[237],"6.42x":[238],"GOPS/Slice,":[240],"10.92x":[242],"GOPS/W":[244],"state-of-the-art":[248],"architecture.":[250],"top-5":[252],"accuracy":[253],"stochastic":[255],"VGG-16":[256],"86.77":[259],"percent":[260],"18.91":[262],"fps":[263],"frame":[264],"rate.":[265]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}