{"id":"https://openalex.org/W2988246957","doi":"https://doi.org/10.1109/fpl.2019.00036","title":"FPGA-Based Training Accelerator Utilizing Sparseness of Convolutional Neural Network","display_name":"FPGA-Based Training Accelerator Utilizing Sparseness of Convolutional Neural Network","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2988246957","doi":"https://doi.org/10.1109/fpl.2019.00036","mag":"2988246957"},"language":"en","primary_location":{"id":"doi:10.1109/fpl.2019.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2019.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 29th International Conference on Field Programmable Logic and Applications (FPL)","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/A5070734898","display_name":"Hiroki Nakahara","orcid":"https://orcid.org/0000-0002-5701-7466"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroki Nakahara","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089957553","display_name":"Youki Sada","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Youki Sada","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043084588","display_name":"Masayuki Shimoda","orcid":"https://orcid.org/0000-0003-4627-0957"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Shimoda","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062308709","display_name":"Kouki Sayama","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouki Sayama","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016922897","display_name":"Akira Jinguji","orcid":"https://orcid.org/0000-0001-5691-3472"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Jinguji","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101424734","display_name":"Shimpei Sato","orcid":"https://orcid.org/0000-0003-0292-1391"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shimpei Sato","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070734898"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.2158,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.83721895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"186"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8450472354888916},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8039893507957458},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7577299475669861},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6616408824920654},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5787379145622253},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5592870116233826},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5206431746482849},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5104492902755737},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5021741390228271},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.47450679540634155},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40586286783218384},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.39911800622940063},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3959331512451172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3263949155807495},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3217346668243408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450472354888916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8039893507957458},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7577299475669861},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6616408824920654},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5787379145622253},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5592870116233826},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5206431746482849},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5104492902755737},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5021741390228271},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.47450679540634155},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40586286783218384},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.39911800622940063},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3959331512451172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3263949155807495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3217346668243408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpl.2019.00036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2019.00036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 29th International Conference on Field Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W634004780","https://openalex.org/W1498436455","https://openalex.org/W1503398984","https://openalex.org/W1547840952","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1935978687","https://openalex.org/W2009832130","https://openalex.org/W2013237284","https://openalex.org/W2053968820","https://openalex.org/W2094756095","https://openalex.org/W2119144962","https://openalex.org/W2149933564","https://openalex.org/W2163605009","https://openalex.org/W2503931548","https://openalex.org/W2557355796","https://openalex.org/W2593303827","https://openalex.org/W2612445135","https://openalex.org/W2625457103","https://openalex.org/W2787513570","https://openalex.org/W2799042347","https://openalex.org/W2808794272","https://openalex.org/W2890068895","https://openalex.org/W2905117322","https://openalex.org/W2962835968","https://openalex.org/W2963911037","https://openalex.org/W2964164125","https://openalex.org/W2964299589","https://openalex.org/W4285719527","https://openalex.org/W4294560677","https://openalex.org/W4297736277","https://openalex.org/W4297775537","https://openalex.org/W4299518610","https://openalex.org/W6630177651","https://openalex.org/W6632552335","https://openalex.org/W6637242042","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6663975638","https://openalex.org/W6677580257","https://openalex.org/W6682132143","https://openalex.org/W6684191040","https://openalex.org/W6730248441","https://openalex.org/W6734621401","https://openalex.org/W6737664043","https://openalex.org/W6748319235","https://openalex.org/W6750964650","https://openalex.org/W6753182402"],"related_works":["https://openalex.org/W3024389224","https://openalex.org/W2959500052","https://openalex.org/W2781923075","https://openalex.org/W2989991345","https://openalex.org/W2435792570","https://openalex.org/W2897186690","https://openalex.org/W2295680811","https://openalex.org/W2770717529","https://openalex.org/W3045877795","https://openalex.org/W2565158842"],"abstract_inverted_index":{"Training":[0],"of":[1,13,20,42,47],"convolutional":[2,49],"neural":[3],"networks":[4],"(CNNs)":[5],"is":[6],"almost":[7],"exclusively":[8],"performed":[9],"on":[10,138,157],"large":[11,71],"clusters":[12],"GPUs.":[14],"However,":[15],"it":[16,103,127],"consumes":[17],"vast":[18],"amounts":[19],"power.":[21],"Thus,":[22,126],"high-speed":[23],"training":[24,37,100,112,120,136,155],"systems":[25],"superior":[26],"in":[27,77],"low-power":[28],"consumption":[29],"are":[30],"desired.":[31],"This":[32],"paper":[33],"proposes":[34],"an":[35],"FPGA-based":[36],"accelerator":[38,137,156],"utilizing":[39],"a":[40,43,84,89,139],"sparseness":[41],"CNN,":[44],"which":[45,87],"consists":[46],"universal":[48,59],"units":[50,53],"and":[51,73,122,170],"pooling":[52],"with":[54],"distributed":[55],"stacks.":[56],"The":[57],"proposed":[58,135,152],"convolution":[60,64],"architecture":[61],"supports":[62],"various":[63],"operations,":[65],"such":[66],"as":[67],"the":[68,78,95,99,119,134,151,158,179],"point-wise,":[69],"depth-wise,":[70],"kernel":[72],"atrous":[74],"convolutions":[75],"used":[76],"modern":[79],"CNN.":[80],"Additionally,":[81],"we":[82],"utilize":[83],"fine-tuning":[85],"scheme,":[86],"loads":[88],"pre-trained":[90],"dense":[91],"CNN":[92,154],"to":[93,107,117,178],"reduce":[94,123],"memory":[96],"size":[97],"for":[98],"process,":[101],"while":[102],"considers":[104],"important":[105],"connectivity":[106],"preserve":[108],"recognition":[109],"accuracy.":[110],"Our":[111],"scheme":[113],"reduces":[114],"85%":[115],"parameters":[116],"accelerate":[118],"computation":[121],"on-chip":[124],"size.":[125],"eliminates":[128],"energy-consuming":[129],"DRAM":[130],"accesses.":[131],"We":[132],"implemented":[133],"Xilinx":[140],"Virtex":[141],"UltraScale+":[142],"VC1525":[143],"acceleration":[144],"development":[145],"board.":[146],"Experimental":[147],"results":[148],"show":[149],"that":[150],"sparse":[153],"FPGA":[159],"can":[160],"achieve":[161],"four":[162],"times":[163,166,172],"faster,":[164],"2.9":[165],"lower":[167],"power":[168],"consumption,":[169],"11.6":[171],"better":[173],"performance":[174],"per":[175],"power,":[176],"compared":[177],"existing":[180],"NVIDIA":[181],"RTX2080Ti":[182],"GPU.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6}],"updated_date":"2026-02-28T09:26:25.869077","created_date":"2025-10-10T00:00:00"}