{"id":"https://openalex.org/W4323854302","doi":"https://doi.org/10.1142/s0218126623502547","title":"Optimizing FPGA-Based Convolutional Neural Network Performance","display_name":"Optimizing FPGA-Based Convolutional Neural Network Performance","publication_year":2023,"publication_date":"2023-03-10","ids":{"openalex":"https://openalex.org/W4323854302","doi":"https://doi.org/10.1142/s0218126623502547"},"language":"en","primary_location":{"id":"doi:10.1142/s0218126623502547","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126623502547","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-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/A5055151952","display_name":"Chi\u2010Chou Kao","orcid":"https://orcid.org/0000-0003-3174-9367"},"institutions":[{"id":"https://openalex.org/I134793997","display_name":"National University of Tainan","ror":"https://ror.org/020pqc882","country_code":"TW","type":"education","lineage":["https://openalex.org/I134793997"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chi-Chou Kao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National University of Tainan, Tainan City 700, Taiwan, R. O. C","Department of Computer Science and Information Engineering, National University of Tainan, Tainan City 700, Taiwan, R. O. China"],"raw_orcid":"https://orcid.org/0000-0003-3174-9367","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National University of Tainan, Tainan City 700, Taiwan, R. O. C","institution_ids":["https://openalex.org/I134793997"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National University of Tainan, Tainan City 700, Taiwan, R. O. China","institution_ids":["https://openalex.org/I134793997"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055151952"],"corresponding_institution_ids":["https://openalex.org/I134793997"],"apc_list":null,"apc_paid":null,"fwci":0.4553,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62070988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"32","issue":"15","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.8560085296630859},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6987001895904541},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.685748279094696},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5895320177078247},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5672634243965149},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5214037895202637},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5157871246337891},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4710783064365387},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4604990482330322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45648834109306335},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44879499077796936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3967835307121277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38110440969467163},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.32698461413383484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560085296630859},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6987001895904541},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.685748279094696},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5895320177078247},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5672634243965149},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5214037895202637},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5157871246337891},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4710783064365387},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4604990482330322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45648834109306335},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44879499077796936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3967835307121277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38110440969467163},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32698461413383484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218126623502547","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126623502547","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1983364832","https://openalex.org/W2289252105","https://openalex.org/W2604272474"],"related_works":["https://openalex.org/W4313341326","https://openalex.org/W4390693267","https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W4388893884","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W4285346947","https://openalex.org/W3145095675"],"abstract_inverted_index":{"In":[0],"deep":[1],"learning,":[2],"convolutional":[3],"neural":[4,12,107],"networks":[5,13],"(CNNs)":[6],"are":[7,23],"a":[8,132],"class":[9],"of":[10,39,75,92],"artificial":[11],"(ANNs),":[14],"most":[15],"commonly":[16],"applied":[17],"to":[18,88,104,113,180],"analyze":[19],"visual":[20],"imagery.":[21],"They":[22],"also":[24],"known":[25,54],"as":[26,55],"Shift-Invariant":[27],"or":[28,43],"Space-Invariant":[29],"Artificial":[30],"Neural":[31],"Networks":[32],"(SIANNs),":[33],"based":[34,63],"on":[35,64,150],"the":[36,40,73,90,106,151,155,171,185,194],"shared-weight":[37],"architecture":[38,138],"convolution":[41],"kernels":[42],"filters":[44],"that":[45],"slide":[46],"along":[47],"input":[48],"features":[49],"and":[50,78,102,118,131,135,141,148,162,184],"provide":[51],"translation-equivariant":[52],"responses":[53],"feature":[56],"maps.":[57],"Recently,":[58],"various":[59],"architectures":[60],"for":[61,154],"CNN":[62,93],"FPGA":[65,152],"platform":[66],"have":[67,145],"been":[68,146],"proposed":[69,156,159,186],"because":[70],"it":[71],"has":[72],"advantages":[74],"high":[76],"performance":[77,91],"fast":[79],"development":[80],"cycle.":[81],"However,":[82],"some":[83],"key":[84],"issues":[85],"including":[86],"how":[87,103],"optimize":[89],"layers":[94],"with":[95,139,174],"different":[96],"structures,":[97],"high-performance":[98],"heterogeneous":[99],"accelerator":[100],"design,":[101],"reduce":[105],"network":[108],"framework":[109],"integration":[110],"overhead":[111],"need":[112],"be":[114],"improved.":[115],"To":[116],"overcome":[117],"improve":[119],"these":[120],"problems,":[121],"we":[122,177],"propose":[123],"dynamic":[124,160],"cycle":[125],"pipeline":[126],"tiling,":[127],"data":[128,163],"layout":[129,164],"optimization,":[130],"pipelined":[133],"software":[134],"hardware":[136],"(SW\u2013HW)-integrated":[137],"flexibility":[140],"integration.":[142],"Some":[143],"benchmarks":[144],"tested":[147],"implemented":[149],"board":[153],"architecture.":[157],"The":[158],"tiling":[161],"transformation":[165],"improved":[166],"by":[167],"2.3":[168],"times":[169,182,190],"in":[170],"performance.":[172],"Moreover,":[173],"two-level":[175],"pipelining,":[176],"achieve":[178],"up":[179],"five":[181],"speedup":[183],"system":[187],"is":[188],"3.8":[189],"more":[191],"energy-efficient":[192],"than":[193],"GPU.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}