{"id":"https://openalex.org/W2907163239","doi":"https://doi.org/10.1109/dasip.2018.8596871","title":"POLYBiNN: A Scalable and Efficient Combinatorial Inference Engine for Neural Networks on FPGA","display_name":"POLYBiNN: A Scalable and Efficient Combinatorial Inference Engine for Neural Networks on FPGA","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2907163239","doi":"https://doi.org/10.1109/dasip.2018.8596871","mag":"2907163239"},"language":"en","primary_location":{"id":"doi:10.1109/dasip.2018.8596871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasip.2018.8596871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Conference on Design and Architectures for Signal and Image Processing (DASIP)","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/A5103051959","display_name":"Ahmed M. Abdelsalam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ahmed M. Abdelsalam","raw_affiliation_strings":["Department of Computer and Software Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Software Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007464582","display_name":"Ahmed H. Elsheikh","orcid":"https://orcid.org/0000-0003-3580-7309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Elsheikh","raw_affiliation_strings":["Department of Mathematics and Industrial Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Industrial Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067086966","display_name":"Jean\u2010Pierre David","orcid":"https://orcid.org/0000-0002-7707-0483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Pierre David","raw_affiliation_strings":["Department of Electrical Engineering, Olytechnique Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Olytechnique Montr\u00e9al, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032933923","display_name":"J. M. Pierre Langlois","orcid":"https://orcid.org/0000-0003-1721-2520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. M. Pierre Langlois","raw_affiliation_strings":["Department of Computer and Software Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Software Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103051959"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68429704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9966999888420105,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.795344889163971},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7462332844734192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207375168800354},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6725873351097107},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5816062092781067},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.5725278854370117},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43002766370773315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3774931728839874},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34735873341560364},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12416049838066101}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.795344889163971},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7462332844734192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207375168800354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6725873351097107},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5816062092781067},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.5725278854370117},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43002766370773315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774931728839874},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34735873341560364},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12416049838066101}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dasip.2018.8596871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasip.2018.8596871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Conference on Design and Architectures for Signal and Image Processing (DASIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:42477","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/42477/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5899999737739563,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1844620123","https://openalex.org/W1887369574","https://openalex.org/W1902934009","https://openalex.org/W1994143452","https://openalex.org/W2014610539","https://openalex.org/W2028166238","https://openalex.org/W2104709228","https://openalex.org/W2112796928","https://openalex.org/W2119144962","https://openalex.org/W2125818553","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2565125333","https://openalex.org/W2583383421","https://openalex.org/W2585560244","https://openalex.org/W2604319603","https://openalex.org/W2619171966","https://openalex.org/W2766839578","https://openalex.org/W2799061466","https://openalex.org/W2919115771","https://openalex.org/W2963114950","https://openalex.org/W2963526839","https://openalex.org/W2964299589","https://openalex.org/W3102169921","https://openalex.org/W3118608800","https://openalex.org/W4302161581","https://openalex.org/W6639703010","https://openalex.org/W6677580257","https://openalex.org/W6698200048","https://openalex.org/W6700264148","https://openalex.org/W6787972765","https://openalex.org/W7014191107"],"related_works":["https://openalex.org/W2095345650","https://openalex.org/W2773582656","https://openalex.org/W2002703587","https://openalex.org/W3217667592","https://openalex.org/W2980006224","https://openalex.org/W2063534976","https://openalex.org/W2284838239","https://openalex.org/W1975010174","https://openalex.org/W2320205417","https://openalex.org/W4308084229"],"abstract_inverted_index":{"Deep":[0],"Neural":[1,6],"Networks":[2,7],"(DNNs)":[3],"and":[4,16,22,53,65,76,83,100,107,120,214],"Convolutional":[5],"(CNNs)":[8],"have":[9],"gained":[10],"significant":[11],"popularity":[12],"in":[13,157,206],"several":[14],"classification":[15],"regression":[17],"applications.":[18],"The":[19,163,188],"massive":[20],"computation":[21],"memory":[23,124],"requirements":[24],"of":[25,55,88,91,105,140,168,191,211],"deep":[26,61],"NN":[27],"architectures":[28],"pose":[29],"particular":[30],"challenges":[31],"for":[32,81,144,151],"their":[33],"FPGA":[34,161],"implementation.":[35],"Moreover,":[36],"programming":[37],"FPGAs":[38,56],"requires":[39],"hardware-specific":[40],"knowledge":[41],"that":[42,133],"many":[43],"machine-learning":[44],"researchers":[45],"do":[46],"not":[47],"possess.":[48],"To":[49],"make":[50],"the":[51,112,141,152,182,207,219],"power":[52,189],"versatility":[54],"available":[57],"to":[58,66,170,218],"a":[59,74,89,123,131,136,145,158,166,212],"wider":[60],"learning":[62],"user":[63],"community":[64],"improve":[67],"DNN":[68],"design":[69],"efficiency,":[70],"we":[71],"introduce":[72],"POLYBiNN,":[73],"scalable":[75],"efficient":[77],"combinatorial":[78],"inference":[79,126],"engine":[80],"DNNs":[82],"CNNs.":[84],"POLYBiNN":[85,109,143,150,202],"is":[86,122,193],"composed":[87],"stack":[90],"decision":[92],"trees,":[93],"which":[94],"are":[95],"binary":[96],"classifiers":[97],"by":[98],"nature,":[99],"utilizes":[101],"AND-OR":[102],"gates":[103],"instead":[104],"multipliers":[106],"accumulators.":[108],"drastically":[110],"cuts":[111],"hardware":[113,138],"consumption":[114,190],"down":[115],"while":[116],"maintaining":[117],"high":[118],"accuracy,":[119],"it":[121],"free":[125],"engine.":[127],"We":[128,148,198],"also":[129,199],"propose":[130],"tool":[132],"generates":[134],"automatically":[135],"low-level":[137],"description":[139],"trained":[142],"given":[146],"application.":[147],"evaluate":[149],"MNIST":[153,183],"dataset":[154,184],"when":[155],"implemented":[156],"ZYNQ-7000":[159],"ZC706":[160],"platform.":[162],"system":[164],"achieves":[165],"throughput":[167],"up":[169],"100":[171],"million":[172],"image":[173],"classifications":[174],"per":[175],"second":[176],"with":[177,185],"90":[178],"ns":[179],"latency":[180],"on":[181],"97.18%":[186],"accuracy.":[187],"PLOYBiNN":[192],"less":[194],"than":[195],"1.2":[196],"W.":[197],"show":[200],"how":[201],"can":[203],"be":[204],"used":[205],"fully":[208],"connected":[209],"layers":[210],"CNN":[213],"apply":[215],"this":[216],"approach":[217],"CIFAR-10":[220],"dataset.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}