{"id":"https://openalex.org/W2784019910","doi":"https://doi.org/10.1109/asicon.2017.8252656","title":"A layer-based structured design of CNN on FPGA","display_name":"A layer-based structured design of CNN on FPGA","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2784019910","doi":"https://doi.org/10.1109/asicon.2017.8252656","mag":"2784019910"},"language":"en","primary_location":{"id":"doi:10.1109/asicon.2017.8252656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asicon.2017.8252656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 12th International Conference on ASIC (ASICON)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043805894","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0001-6232-798X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005129815","display_name":"Siyu Ni","orcid":"https://orcid.org/0000-0003-3634-5599"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Ni","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006212733","display_name":"Gengsheng Chen","orcid":"https://orcid.org/0000-0003-1879-9415"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengsheng Chen","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1037","last_page":"1040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9933000206947327,"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/T10320","display_name":"Neural Networks and Applications","score":0.986299991607666,"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":0.8526354432106018},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8298885822296143},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7377451658248901},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6933196783065796},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6877991557121277},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4746870696544647},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4480293095111847},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.43805286288261414},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43526121973991394},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4101763367652893},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3828376829624176},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3768410086631775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22848433256149292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19129285216331482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526354432106018},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8298885822296143},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7377451658248901},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6933196783065796},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6877991557121277},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4746870696544647},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4480293095111847},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43805286288261414},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43526121973991394},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4101763367652893},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3828376829624176},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3768410086631775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22848433256149292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19129285216331482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asicon.2017.8252656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asicon.2017.8252656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 12th International Conference on ASIC (ASICON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3023634467","https://openalex.org/W4239047192","https://openalex.org/W4241365061"],"related_works":["https://openalex.org/W2503642292","https://openalex.org/W4295127407","https://openalex.org/W2995926156","https://openalex.org/W2063534976","https://openalex.org/W4382657987","https://openalex.org/W2284838239","https://openalex.org/W2056818248","https://openalex.org/W2796942851","https://openalex.org/W1975010174","https://openalex.org/W2524802307"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4,17,72,96],"widely":[5],"used":[6],"in":[7,12,63,66,82,94,128,185],"machine":[8],"learning":[9],"applications.":[10],"Large":[11],"scale,":[13],"most":[14],"deep":[15],"CNNs":[16],"however":[18],"difficult":[19],"to":[20,115],"be":[21],"implemented":[22,138],"on":[23,42],"a":[24,32,38,43,52,117,129,176],"single":[25],"hardware":[26],"for":[27,60,100],"acceleration.":[28],"This":[29,105],"paper":[30],"presents":[31],"new":[33,50,106],"design":[34,56,107],"and":[35,74,77,86,98,102,108,119,160,183],"implementation":[36],"of":[37,146,187],"23-layer":[39,139],"SqueezeNet":[40,140],"[1]":[41],"Xilinx":[44],"VC709":[45],"FPGA":[46,174],"board.":[47],"In":[48],"this":[49],"design,":[51],"novel":[53],"layer-based":[54],"structured":[55],"method":[57],"is":[58,157],"proposed":[59],"full":[61],"scalability":[62],"constructing":[64],"CNNs,":[65],"which":[67,156],"all":[68,123],"the":[69,91,112,136,168],"CNN":[70,114,170],"layers":[71,125],"optimized":[73,99],"deployed":[75],"separately":[76],"independently.":[78],"Moreover,":[79],"inherent":[80],"parallelism":[81],"CNN's":[83],"data":[84,92],"channels":[85],"intra-kernel":[87],"computations,":[88],"together":[89],"with":[90,122,152,167],"structure":[93],"memory,":[95],"exploited":[97],"performance":[101,145,179],"efficiency":[103],"enhancement.":[104],"its":[109,124,143],"architecture":[110],"enables":[111],"whole":[113],"have":[116],"flexible":[118],"scalable":[120],"deployment,":[121],"working":[126],"concurrently":[127],"pipelined":[130],"structure.":[131],"Experimental":[132],"result":[133],"shows":[134,175],"that,":[135],"newly":[137],"can":[141],"reach":[142],"peak":[144],"213.7GOP/s":[147],"under":[148],"110MHz":[149],"clock":[150],"frequency":[151],"79.05%":[153],"top-5":[154],"accuracy,":[155],"much":[158,177],"faster":[159],"more":[161],"efficient":[162],"than":[163,180],"similar":[164],"works.":[165],"Additionally,":[166],"same":[169],"network":[171],"built":[172],"on,":[173],"better":[178],"CPU,":[181],"GPU":[182],"SoC":[184],"terms":[186],"power":[188],"efficiency.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}