{"id":"https://openalex.org/W3127310706","doi":"https://doi.org/10.1109/gcaiot51063.2020.9345815","title":"Weight Compression-Friendly Binarized Neural Network","display_name":"Weight Compression-Friendly Binarized Neural Network","publication_year":2020,"publication_date":"2020-12-12","ids":{"openalex":"https://openalex.org/W3127310706","doi":"https://doi.org/10.1109/gcaiot51063.2020.9345815","mag":"3127310706"},"language":"en","primary_location":{"id":"doi:10.1109/gcaiot51063.2020.9345815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcaiot51063.2020.9345815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","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/A5073565712","display_name":"Yuzhong Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuzhong Jiao","raw_affiliation_strings":["United Microelectronics Centre,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"United Microelectronics Centre,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102804376","display_name":"Xiao Huo","orcid":"https://orcid.org/0000-0003-0287-5196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Huo","raw_affiliation_strings":["United Microelectronics Centre,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"United Microelectronics Centre,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390943","display_name":"Lei Yuan","orcid":"https://orcid.org/0009-0002-7040-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Lei","raw_affiliation_strings":["United Microelectronics Centre,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"United Microelectronics Centre,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077421606","display_name":"Sha Li","orcid":"https://orcid.org/0009-0001-5612-4171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sha Li","raw_affiliation_strings":["United Microelectronics Centre,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"United Microelectronics Centre,Hong Kong,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013608093","display_name":"Yiu Kei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiu Kei Li","raw_affiliation_strings":["United Microelectronics Centre,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"United Microelectronics Centre,Hong Kong,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073565712"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4885,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67211131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.9943000078201294,"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/mnist-database","display_name":"MNIST database","score":0.9521034955978394},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7123585939407349},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6733794212341309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6729052066802979},{"id":"https://openalex.org/keywords/xnor-gate","display_name":"XNOR gate","score":0.6662947535514832},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.483711302280426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4726758599281311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47151339054107666},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4689093828201294},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44574180245399475},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38001811504364014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18240618705749512},{"id":"https://openalex.org/keywords/logic-gate","display_name":"Logic gate","score":0.17135822772979736},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11434760689735413}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.9521034955978394},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7123585939407349},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6733794212341309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729052066802979},{"id":"https://openalex.org/C57684291","wikidata":"https://www.wikidata.org/wiki/Q1336142","display_name":"XNOR gate","level":4,"score":0.6662947535514832},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.483711302280426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4726758599281311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47151339054107666},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4689093828201294},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44574180245399475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38001811504364014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18240618705749512},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.17135822772979736},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11434760689735413},{"id":"https://openalex.org/C124296912","wikidata":"https://www.wikidata.org/wiki/Q575178","display_name":"NAND gate","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcaiot51063.2020.9345815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcaiot51063.2020.9345815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1902934009","https://openalex.org/W2119144962","https://openalex.org/W2267635276","https://openalex.org/W2300242332","https://openalex.org/W2405920868","https://openalex.org/W2469490737","https://openalex.org/W2586654419","https://openalex.org/W2593245696","https://openalex.org/W2770398148","https://openalex.org/W2787884921","https://openalex.org/W2800673081","https://openalex.org/W2809624076","https://openalex.org/W2963114950","https://openalex.org/W2964228333","https://openalex.org/W2964299589","https://openalex.org/W2979872424","https://openalex.org/W3041416753","https://openalex.org/W3143293593","https://openalex.org/W4295262505","https://openalex.org/W6639703010","https://openalex.org/W6677580257","https://openalex.org/W6693397755","https://openalex.org/W6698200048","https://openalex.org/W6780059108"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W2108719777","https://openalex.org/W2910771446","https://openalex.org/W4380078352","https://openalex.org/W3036048022","https://openalex.org/W4309224979","https://openalex.org/W3026879719","https://openalex.org/W2896822060"],"abstract_inverted_index":{"The":[0,15,31,72,98,117,153],"resources":[1,67],"of":[2,18,35,84,94,107,136,163],"edge":[3,24],"devices":[4,25],"in":[5,22,91,130],"AIoT":[6],"systems":[7],"are":[8,100],"usually":[9],"constrained":[10],"with":[11,133,145],"size":[12],"and":[13,48,114],"power.":[14],"computational":[16],"complexity":[17],"neural":[19,37,41,111,164],"network":[20,42,112],"models":[21],"these":[23],"has":[26],"become":[27],"a":[28,108],"major":[29],"concern.":[30],"most":[32],"compact":[33],"form":[34],"deep":[36],"networks":[38],"is":[39,170],"binarized":[40],"(BNN),":[43],"which":[44],"adopts":[45],"binary":[46,54,105],"weights":[47,78],"exclusive":[49],"NOR":[50],"(XNOR)":[51],"operations":[52],"as":[53],"convolution.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"weight":[61,154],"compression-friendly":[62],"BNN":[63,96,175],"to":[64,81],"save":[65],"hardware":[66,176],"by":[68,102],"reducing":[69],"memory":[70,131,143],"space.":[71],"proposed":[73,122,168],"technique":[74,123,169],"does":[75,157],"not":[76,158],"binarize":[77],"just":[79],"according":[80],"the":[82,92,95,104,121,160,167],"signs":[83],"weights,":[85],"but":[86],"fully":[87],"considers":[88],"compression":[89,155],"efficiency":[90],"training":[93],"model.":[97],"experiments":[99],"performed":[101],"using":[103],"version":[106],"6-layer":[109],"convolutional":[110],"(CNN)":[113],"MNIST":[115,151],"case.":[116],"results":[118],"show":[119],"that":[120],"can":[124],"achieve":[125],"more":[126,140],"than":[127,141],"25%":[128],"reduction":[129,144],"space":[132],"accuracy":[134,148],"loss":[135],"1":[137],"%,":[138],"or":[139],"35%":[142],"about":[146],"2.5%":[147],"drop":[149],"for":[150,173],"classification.":[152],"method":[156],"destroy":[159],"regular":[161],"structure":[162],"networks,":[165],"so":[166],"very":[171],"fit":[172],"processor-based":[174],"accelerators.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}