{"id":"https://openalex.org/W2996949662","doi":null,"title":"Exploring FPGA Implementation for Binarized Neural Network Inference","display_name":"Exploring FPGA Implementation for Binarized Neural Network Inference","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2996949662","mag":"2996949662"},"language":"en","primary_location":{"id":"pmh:oai:stars.library.ucf.edu:etd-7205","doi":null,"is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/etd/6205","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,"listed_in":["cwts-core","vabb-shw"],"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":"Electronic Theses and Dissertations","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/etd/6205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100637724","display_name":"Li Yang","orcid":"https://orcid.org/0000-0003-2750-7031","observed_orcids":["https://orcid.org/0000-0003-2750-7031","https://orcid.org/0000-0001-6836-0350"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2750-7031","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100637724"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.951200008392334,"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":0.951200008392334,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.032499998807907104,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T13292","display_name":"Embedded Systems and FPGA Applications","score":0.008799999952316284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binary-neural-networks","display_name":"binary neural networks","score":0.9959999918937683},{"id":"https://openalex.org/keywords/fpga-implementation","display_name":"FPGA implementation","score":0.8809999823570251},{"id":"https://openalex.org/keywords/parallel-convolution","display_name":"parallel convolution","score":0.7059999704360962},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.5950000286102295},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6269999742507935},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9869999885559082},{"id":"https://openalex.org/keywords/on-chip-memory","display_name":"on-chip memory","score":0.7739999890327454},{"id":"https://openalex.org/keywords/embedded-systems","display_name":"embedded systems","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6596822738647461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291589140892029},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5734495520591736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5506448745727539},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5025079250335693},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1998785436153412}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:stars.library.ucf.edu:etd-7205","doi":null,"is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/etd/6205","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,"listed_in":["cwts-core","vabb-shw"],"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":"Electronic Theses and Dissertations","raw_type":"text"},{"id":"mag:2996949662","doi":null,"is_oa":false,"landing_page_url":"https://stars.library.ucf.edu/cgi/viewcontent.cgi?article=7205&context=etd","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:etd-7205","doi":null,"is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/etd/6205","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,"listed_in":["cwts-core","vabb-shw"],"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":"Electronic Theses and Dissertations","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2319920447","https://openalex.org/W2469490737","https://openalex.org/W2565125333","https://openalex.org/W2585560244","https://openalex.org/W2762651727","https://openalex.org/W2949117887","https://openalex.org/W2963114950","https://openalex.org/W2964008506","https://openalex.org/W2964299589"],"related_works":["https://openalex.org/W2889111331","https://openalex.org/W2765235648","https://openalex.org/W2949533017","https://openalex.org/W2682503742","https://openalex.org/W2786065101","https://openalex.org/W2584921118","https://openalex.org/W2724189024","https://openalex.org/W7167486286","https://openalex.org/W7055604642","https://openalex.org/W2585560244"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1,106],"neural":[2,32,60,108,142],"network":[3,109,143,192],"has":[4,144,184],"taken":[5],"an":[6],"important":[7],"role":[8],"in":[9,17],"machine":[10],"learning":[11],"algorithm.":[12],"It":[13,158],"is":[14,41,120],"widely":[15],"used":[16],"different":[18],"areas":[19],"such":[20,46],"as":[21],"computer":[22],"vision,":[23],"robotics,":[24],"and":[25,36,67,71,81,128,133,165,210,246,255],"biology.":[26],"However,":[27],"the":[28,58,78,130,152,176,190,194,229,252],"models":[29],"of":[30,135],"deep":[31],"networks":[33,61],"become":[34],"larger":[35],"more":[37],"computation":[38,82,211],"complexity":[39],"which":[40,84,150,182,204,225,249],"a":[42,103,216],"big":[43],"obstacle":[44],"for":[45,88,122,221],"huge":[47],"model":[48,196],"to":[49,101,259],"implement":[50,102,171],"on":[51,112,125,162,201,239],"embedded":[52,118],"systems.":[53],"Recent":[54],"works":[55],"have":[56],"shown":[57],"binarized":[59,64,72,107,141,147,155],"(BNN),":[62],"utilizing":[63],"(i.e.":[65,110],"+1":[66],"-1)":[68],"convolution":[69,148,156],"kernel":[70],"activation":[73],"function,":[74],"can":[75,198,205,226],"significantly":[76],"reduce":[77,207],"parameter":[79,168],"size":[80],"cost,":[83],"makes":[85],"it":[86],"hardware-friendly":[87],"Field-Programmable":[89],"Gate":[90],"Arrays":[91],"(FPGAs)":[92],"implementation":[93],"with":[94,114],"efficient":[95],"energy":[96,208,256],"cost.":[97],"This":[98],"thesis":[99],"proposes":[100],"new":[104,217],"parallel":[105,146],"PC-BNN)":[111],"FPGA":[113,180,240],"accurate":[115],"inference.":[116],"The":[117,139,231],"PC-BNN":[119,173,222,237],"designed":[121],"image":[123],"classification":[124],"CIFAR-10":[126,163],"dataset":[127,164],"explores":[129],"hardware":[131,223],"architecture":[132,220],"optimization":[134],"customized":[136],"CNN":[137],"topology.":[138],"parallel-convolution":[140],"two":[145],"layers":[149],"replaces":[151],"original":[153],"single":[154],"layer.":[157],"achieves":[159,241],"around":[160],"86%":[161],"owns":[166],"2.3Mb":[167],"size.":[169],"We":[170],"our":[172,236],"inference":[174,224,238],"into":[175],"Xilinx":[177],"PYNQ":[178],"Z1":[179],"board":[181],"only":[183],"4.9Mb":[185],"on-chip":[186,202],"Block":[187],"RAM.":[188],"Since":[189],"ultra-small":[191],"parameter,":[193],"whole":[195],"parameters":[197],"be":[199],"stored":[200],"memory":[203],"greatly":[206],"consumption":[209],"latency.":[212],"Meanwhile,":[213],"we":[214],"design":[215],"pipeline":[218],"streaming":[219],"further":[227],"increase":[228],"performance.":[230],"experiment":[232],"results":[233],"show":[234],"that":[235],"930":[242],"frames":[243],"per":[244],"second":[245],"387.5":[247],"FPS/Watt,":[248],"are":[250],"among":[251],"best":[253],"throughput":[254],"efficiency":[257],"compared":[258],"most":[260],"recent":[261],"works.":[262]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-01-10T00:00:00"}