{"id":"https://openalex.org/W2890311316","doi":"https://doi.org/10.1109/icassp.2018.8461456","title":"True Gradient-Based Training of Deep Binary Activated Neural Networks Via Continuous Binarization","display_name":"True Gradient-Based Training of Deep Binary Activated Neural Networks Via Continuous Binarization","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890311316","doi":"https://doi.org/10.1109/icassp.2018.8461456","mag":"2890311316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047303294","display_name":"Charbel Sakr","orcid":"https://orcid.org/0000-0001-5641-0541"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charbel Sakr","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078440061","display_name":"Jungwook Choi","orcid":"https://orcid.org/0000-0002-3075-8694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungwook Choi","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023418635","display_name":"Zhuo Wang","orcid":"https://orcid.org/0000-0002-4582-3401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Wang","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101429456","display_name":"Kailash Gopalakrishnan","orcid":"https://orcid.org/0000-0002-8952-0875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kailash Gopalakrishnan","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057014407","display_name":"Naresh R. Shanbhag","orcid":"https://orcid.org/0000-0002-4323-9164"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naresh Shanbhag","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2346","last_page":"2350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9962999820709229,"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":0.765548825263977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7374352216720581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6858323216438293},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6430550813674927},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6363963484764099},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6175720691680908},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6144098043441772},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5693196058273315},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48670127987861633},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.48500439524650574},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4542139768600464},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4450148344039917},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.44083431363105774},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.4387041926383972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4271736145019531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42495957016944885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37460434436798096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12056714296340942}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.765548825263977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374352216720581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6858323216438293},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6430550813674927},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6363963484764099},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6175720691680908},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6144098043441772},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5693196058273315},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48670127987861633},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.48500439524650574},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4542139768600464},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4450148344039917},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.44083431363105774},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.4387041926383972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4271736145019531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42495957016944885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37460434436798096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12056714296340942},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1522301498","https://openalex.org/W1841592590","https://openalex.org/W1902934009","https://openalex.org/W2104636679","https://openalex.org/W2145287260","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2286365479","https://openalex.org/W2289252105","https://openalex.org/W2300242332","https://openalex.org/W2331143823","https://openalex.org/W2335728318","https://openalex.org/W2469490737","https://openalex.org/W2741318576","https://openalex.org/W2963114950","https://openalex.org/W2963516298","https://openalex.org/W2963674932","https://openalex.org/W3118608800","https://openalex.org/W4240805545","https://openalex.org/W4295262505","https://openalex.org/W6638783484","https://openalex.org/W6639703010","https://openalex.org/W6675722231","https://openalex.org/W6681342084","https://openalex.org/W6684191040","https://openalex.org/W6693397755","https://openalex.org/W6696004547","https://openalex.org/W6698200048","https://openalex.org/W6701947533","https://openalex.org/W6703116779","https://openalex.org/W6742116046"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W4389249638","https://openalex.org/W2733410219","https://openalex.org/W3211208177","https://openalex.org/W4205124255"],"abstract_inverted_index":{"With":[0],"the":[1,8,61,65,73,76,114,134,169,183,189],"ever":[2],"growing":[3],"popularity":[4],"of":[5,11,75,168],"deep":[6,12],"learning,":[7],"tremendous":[9],"complexity":[10],"neural":[13,87,103],"networks":[14,27,88,104],"is":[15,111],"becoming":[16],"problematic":[17],"when":[18,181],"one":[19],"considers":[20],"inference":[21],"on":[22,54,143],"resource":[23],"constrained":[24],"platforms.":[25],"Binary":[26],"have":[28],"emerged":[29],"as":[30,43,172,177,179],"a":[31,37,80,96],"potential":[32],"solution,":[33],"however,":[34],"they":[35],"exhibit":[36],"fundamentallimi-tation":[38],"in":[39,57,83],"realizing":[40],"gradient-based":[41,107,161],"learning":[42,162],"their":[44,90],"activations":[45],"are":[46],"non-differentiable.":[47],"Current":[48],"work":[49],"has":[50,127],"so":[51],"far":[52],"relied":[53],"approximating":[55],"gradients":[56],"order":[58],"to":[59,99,133,174],"use":[60],"back-propagation":[62],"algorithm":[63],"via":[64],"straight":[66],"through":[67],"estimator":[68],"(STE).":[69],"Such":[70],"approximations":[71],"harm":[72],"quality":[74],"training":[77,182],"procedure":[78],"causing":[79],"noticeable":[81],"gap":[82],"accuracy":[84,129,165,175],"between":[85,116],"binary":[86,101,119,185],"and":[89,118,149],"full":[91,135],"precision":[92,136],"baselines.":[93],"We":[94,122],"present":[95],"novel":[97],"method":[98,126,142],"train":[100],"activated":[102,186],"using":[105,159,188],"true":[106,160],"learning.":[108],"Our":[109],"idea":[110],"motivated":[112],"by":[113],"similarities":[115],"clipping":[117],"activation":[120],"functions.":[121],"show":[123,155],"that":[124,156],"our":[125,141],"minimal":[128],"degradation":[130],"with":[131],"respect":[132],"baseline.":[137],"Finally,":[138],"we":[139,154],"test":[140],"three":[144],"benchmarking":[145],"datasets:":[146],"MNIST,":[147],"CIFAR-10,":[148],"SVHN.":[150],"For":[151],"each":[152],"benchmark,":[153],"continuous":[157],"binarization":[158],"achieves":[163],"an":[164],"within":[166],"1.5%":[167],"floating-point":[170],"baseline,":[171],"compared":[173],"drops":[176],"high":[178],"6%":[180],"same":[184],"network":[187],"STE.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}