{"id":"https://openalex.org/W4308536741","doi":"https://doi.org/10.1109/nas55553.2022.9925552","title":"Hardware-Efficient Template-Based Deep CNNs Accelerator Design","display_name":"Hardware-Efficient Template-Based Deep CNNs Accelerator Design","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4308536741","doi":"https://doi.org/10.1109/nas55553.2022.9925552"},"language":"en","primary_location":{"id":"doi:10.1109/nas55553.2022.9925552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas55553.2022.9925552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Networking, Architecture and Storage (NAS)","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/A5040075095","display_name":"Azzam Alhussain","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azzam Alhussain","raw_affiliation_strings":["College of Engineering and Computer Science, University of Central Florida Orlando,Florida,USA","College of Engineering and Computer Science, University of Central Florida Orlando, Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, University of Central Florida Orlando,Florida,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"College of Engineering and Computer Science, University of Central Florida Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["College of Engineering and Computer Science, University of Central Florida Orlando,Florida,USA","College of Engineering and Computer Science, University of Central Florida Orlando, Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, University of Central Florida Orlando,Florida,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"College of Engineering and Computer Science, University of Central Florida Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.4623,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72498427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9988999962806702,"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":0.8527267575263977},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7437267899513245},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7385267019271851},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.6654613018035889},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6526421308517456},{"id":"https://openalex.org/keywords/cellular-neural-network","display_name":"Cellular neural network","score":0.4849970042705536},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48075056076049805},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4645393192768097},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4313932955265045},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4206172525882721},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4100925922393799},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33973413705825806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3390958905220032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32582026720046997},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31906795501708984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23675328493118286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8527267575263977},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7437267899513245},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7385267019271851},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6654613018035889},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6526421308517456},{"id":"https://openalex.org/C812465","wikidata":"https://www.wikidata.org/wiki/Q5058375","display_name":"Cellular neural network","level":3,"score":0.4849970042705536},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48075056076049805},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4645393192768097},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4313932955265045},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4206172525882721},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4100925922393799},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33973413705825806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3390958905220032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32582026720046997},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31906795501708984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23675328493118286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas55553.2022.9925552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas55553.2022.9925552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Networking, Architecture and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.41999998688697815,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2094756095","https://openalex.org/W2096733369","https://openalex.org/W2117696986","https://openalex.org/W2194775991","https://openalex.org/W2295680811","https://openalex.org/W2616014673","https://openalex.org/W2618530766","https://openalex.org/W2754396617","https://openalex.org/W2810861508","https://openalex.org/W2891946740","https://openalex.org/W2962835968","https://openalex.org/W3013892238","https://openalex.org/W3210521911","https://openalex.org/W4242577057"],"related_works":["https://openalex.org/W2998381397","https://openalex.org/W2187181201","https://openalex.org/W2532502681","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Acceleration":[0],"of":[1,52,124,134],"Convolutional":[2],"Neural":[3],"Network":[4],"(CNN)":[5],"on":[6,128,153],"edge":[7],"devices":[8],"has":[9],"recently":[10],"achieved":[11],"a":[12,38,100,121],"remarkable":[13],"performance":[14,55,123,157],"in":[15,99],"image":[16],"classification":[17],"and":[18,27,42,68,72,84,93,113,116,131,141],"object":[19],"detection":[20],"applications.":[21],"This":[22],"paper":[23],"proposes":[24],"an":[25,48],"efficient":[26],"scalable":[28],"CNN-based":[29],"SoC-FPGA":[30],"accelerator":[31,107],"design":[32],"that":[33],"takes":[34],"pre-trained":[35],"weights":[36],"with":[37,78,120],"16-bit":[39],"fixed-point":[40],"quantization":[41],"target":[43],"hardware":[44],"specification":[45],"to":[46,81],"generate":[47],"optimized":[49],"template":[50,61],"capable":[51],"achieving":[53],"higher":[54,156],"versus":[56],"resource":[57],"utilization":[58],"trade-off.":[59],"The":[60],"analyzed":[62],"the":[63,106,150],"computational":[64],"workload,":[65],"data":[66],"dependency,":[67],"external":[69],"memory":[70],"bandwidth":[71],"utilized":[73],"loop":[74],"tiling":[75],"transformation":[76],"along":[77],"dataflow":[79],"modeling":[80],"convert":[82],"convolutional":[83],"fully":[85],"connected":[86],"layers":[87],"into":[88],"vector":[89],"multiplication":[90],"between":[91],"input":[92],"output":[94],"feature":[95],"maps,":[96],"which":[97],"resulted":[98],"single":[101],"compute":[102,136],"unit":[103,137],"on-chip.":[104],"Furthermore,":[105],"was":[108,147],"examined":[109],"among":[110],"AlexNet,":[111],"VGG16,":[112],"LeNet":[114],"networks":[115],"ran":[117],"at":[118],"200-MHz":[119],"peak":[122],"230":[125],"GOP/s":[126],"depending":[127],"ZYNQ":[129],"boards":[130],"state-space":[132],"exploration":[133],"different":[135],"configurations":[138],"during":[139],"simulation":[140],"synthesis.":[142],"Lastly,":[143],"our":[144],"proposed":[145],"methodology":[146],"benchmarked":[148],"against":[149],"previous":[151],"development":[152],"Ultra96":[154],"for":[155],"measurement.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}