{"id":"https://openalex.org/W2787094505","doi":"https://doi.org/10.1109/fpt.2017.8280142","title":"An FPGA-based processor for training convolutional neural networks","display_name":"An FPGA-based processor for training convolutional neural networks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787094505","doi":"https://doi.org/10.1109/fpt.2017.8280142","mag":"2787094505"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2017.8280142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100677604","display_name":"Zhiqiang Liu","orcid":"https://orcid.org/0009-0000-1143-9340"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqiang Liu","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069310600","display_name":"Jingfei Jiang","orcid":"https://orcid.org/0000-0002-7103-8650"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfei Jiang","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367009","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-7078-7545"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035437657","display_name":"Paul Chow","orcid":"https://orcid.org/0000-0002-0523-7117"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Paul Chow","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100677604"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.9249,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.84608792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8766927719116211},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7391060590744019},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7002049684524536},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6875593066215515},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5479595065116882},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.545695960521698},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5258883833885193},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5171396136283875},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47982096672058105},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4126982092857361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19669055938720703},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17999881505966187},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07319489121437073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8766927719116211},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7391060590744019},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7002049684524536},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6875593066215515},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5479595065116882},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.545695960521698},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5258883833885193},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5171396136283875},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47982096672058105},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4126982092857361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19669055938720703},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17999881505966187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07319489121437073}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2017.8280142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1950136256","https://openalex.org/W1963882359","https://openalex.org/W2009832130","https://openalex.org/W2074772891","https://openalex.org/W2094756095","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2120284346","https://openalex.org/W2144354855","https://openalex.org/W2163605009","https://openalex.org/W2276486856","https://openalex.org/W2557355796","https://openalex.org/W2574797063","https://openalex.org/W2585774018","https://openalex.org/W3004171485","https://openalex.org/W6684191040","https://openalex.org/W6694717790"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W3138386522","https://openalex.org/W2499279132","https://openalex.org/W4225949190","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W121182129"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"gained":[5],"great":[6],"success":[7],"in":[8,59,65,104],"various":[9],"computer":[10],"vision":[11],"applications.":[12],"However,":[13],"training":[14,23,50,67],"a":[15,89,115,130],"CNN":[16,63,133],"model":[17],"is":[18,24,74,93,111,139],"computation-intensive":[19],"and":[20,36],"time-consuming.":[21],"Hence":[22],"mainly":[25],"processed":[26],"on":[27,85,117,129,148],"large":[28],"clusters":[29],"of":[30,52,62,82,132],"high-performance":[31],"processors":[32],"like":[33],"server":[34],"CPUs":[35],"GPUs.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"an":[43],"FPGA-based":[44],"processor":[45,116,138],"design":[46,73,110],"to":[47,76,141],"accelerate":[48],"the":[49,57,66,86,97,102,118,145,149],"process":[51],"CNNs.":[53],"We":[54],"first":[55],"analyze":[56],"operations":[58,83],"all":[60,80],"types":[61],"layers":[64],"process.":[68],"A":[69],"uniform":[70],"computation":[71],"engine":[72],"proposed":[75,108],"efficiently":[77],"carry":[78],"out":[79],"kinds":[81],"based":[84],"analysis.":[87],"Then":[88],"scalable":[90],"accelerator":[91,109],"framework":[92],"presented":[94],"that":[95,136],"exploits":[96],"parallelism":[98],"further":[99],"by":[100,113],"unrolling":[101],"loops":[103],"two":[105],"levels.":[106],"The":[107,126],"demonstrated":[112],"implementing":[114],"Xilinx":[119],"ZU19EG":[120],"FPGA":[121],"working":[122],"at":[123],"200":[124],"MHz.":[125],"evaluation":[127],"results":[128],"group":[131],"models":[134],"show":[135],"our":[137],"5.7":[140],"10.7-fold":[142],"faster":[143],"than":[144],"software":[146],"implementations":[147],"Intel":[150],"Core":[151],"i5-4440":[152],"CPU(@3.10GHz).":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}