{"id":"https://openalex.org/W4379644764","doi":"https://doi.org/10.1145/3555776.3577674","title":"Are alternatives to backpropagation useful for training Binary Neural Networks? An experimental study in image classification","display_name":"Are alternatives to backpropagation useful for training Binary Neural Networks? An experimental study in image classification","publication_year":2023,"publication_date":"2023-03-27","ids":{"openalex":"https://openalex.org/W4379644764","doi":"https://doi.org/10.1145/3555776.3577674"},"language":"en","primary_location":{"id":"doi:10.1145/3555776.3577674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555776.3577674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04161529v1/file/SAC_binary_neural_networks.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038396212","display_name":"Ben Crulis","orcid":"https://orcid.org/0000-0002-3132-1136"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ben Crulis","raw_affiliation_strings":["University of Tours, Tours, France","RFAI - Reconnaissance des formes et analyse d'images (64 avenue de Portalis\r\n37200 Tours - France)"],"raw_orcid":"https://orcid.org/0000-0002-3132-1136","affiliations":[{"raw_affiliation_string":"University of Tours, Tours, France","institution_ids":["https://openalex.org/I110017253"]},{"raw_affiliation_string":"RFAI - Reconnaissance des formes et analyse d'images (64 avenue de Portalis\r\n37200 Tours - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103122681","display_name":"Barth\u00e9lemy Serres","orcid":"https://orcid.org/0000-0003-3702-1334"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Barthelemy Serres","raw_affiliation_strings":["University of Tours, Tours, France"],"raw_orcid":"https://orcid.org/0000-0003-3702-1334","affiliations":[{"raw_affiliation_string":"University of Tours, Tours, France","institution_ids":["https://openalex.org/I110017253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032407315","display_name":"Cyril de Runz","orcid":"https://orcid.org/0000-0002-5951-6859"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]},{"id":"https://openalex.org/I4210136805","display_name":"Laboratoire d'Informatique Fondamentale et Appliqu\u00e9e de Tours","ror":"https://ror.org/03r938j26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I110017253","https://openalex.org/I4210136805"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cyril De Runz","raw_affiliation_strings":["LIFAT, University of Tours, Tours, France"],"raw_orcid":"https://orcid.org/0000-0002-5951-6859","affiliations":[{"raw_affiliation_string":"LIFAT, University of Tours, Tours, France","institution_ids":["https://openalex.org/I4210136805","https://openalex.org/I110017253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043476218","display_name":"Gilles Venturini","orcid":"https://orcid.org/0000-0002-8112-2418"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Venturini","raw_affiliation_strings":["University of Tours, Tours, France","RFAI - Reconnaissance des formes et analyse d'images (64 avenue de Portalis\r\n37200 Tours - France)"],"raw_orcid":"https://orcid.org/0000-0002-8112-2418","affiliations":[{"raw_affiliation_string":"University of Tours, Tours, France","institution_ids":["https://openalex.org/I110017253"]},{"raw_affiliation_string":"RFAI - Reconnaissance des formes et analyse d'images (64 avenue de Portalis\r\n37200 Tours - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038396212"],"corresponding_institution_ids":["https://openalex.org/I110017253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04978988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1171","last_page":"1178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10320","display_name":"Neural Networks and Applications","score":0.9977999925613403,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955000281333923,"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/backpropagation","display_name":"Backpropagation","score":0.9051101207733154},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8848528861999512},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7777162790298462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774262547492981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7181944251060486},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5489969849586487},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5463332533836365},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5366786122322083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4742759168148041},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4736168086528778},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4320942759513855},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4166387915611267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38571107387542725},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17188319563865662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07857200503349304}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9051101207733154},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8848528861999512},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7777162790298462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774262547492981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7181944251060486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5489969849586487},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5463332533836365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5366786122322083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4742759168148041},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4736168086528778},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4320942759513855},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4166387915611267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38571107387542725},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17188319563865662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07857200503349304},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3555776.3577674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555776.3577674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04161529v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04161529","pdf_url":"https://hal.science/hal-04161529v1/file/SAC_binary_neural_networks.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAC '23: 38th ACM/SIGAPP Symposium on Applied Computing, 2023, Tallinn, Estonia. pp.1171-1178, ⟨10.1145/3555776.3577674⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04161529v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04161529","pdf_url":"https://hal.science/hal-04161529v1/file/SAC_binary_neural_networks.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAC '23: 38th ACM/SIGAPP Symposium on Applied Computing, 2023, Tallinn, Estonia. pp.1171-1178, ⟨10.1145/3555776.3577674⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379644764.pdf","grobid_xml":"https://content.openalex.org/works/W4379644764.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W196871588","https://openalex.org/W2007339694","https://openalex.org/W2479609865","https://openalex.org/W2552737632","https://openalex.org/W2747329762","https://openalex.org/W2756779681","https://openalex.org/W2949933418","https://openalex.org/W2952265507","https://openalex.org/W2952797486","https://openalex.org/W2978329087","https://openalex.org/W2998249317","https://openalex.org/W3008515144","https://openalex.org/W3091355409","https://openalex.org/W3091594070","https://openalex.org/W3094844246","https://openalex.org/W3121174466","https://openalex.org/W3158825252","https://openalex.org/W3160422373","https://openalex.org/W3167468823","https://openalex.org/W3174657965","https://openalex.org/W3216316796","https://openalex.org/W4205393829"],"related_works":["https://openalex.org/W3008580913","https://openalex.org/W2896628485","https://openalex.org/W1701967867","https://openalex.org/W2115605526","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W4225893763","https://openalex.org/W2788727425","https://openalex.org/W2405196115"],"abstract_inverted_index":{"Current":[0],"artificial":[1,42],"neural":[2,43,52,61,88,111,125,158],"networks":[3,44,53,89,112,159],"are":[4,90],"trained":[5,164],"with":[6],"parameters":[7],"encoded":[8],"as":[9,49,64,66,117],"floating":[10],"point":[11],"numbers":[12],"that":[13,156],"occupy":[14],"lots":[15],"of":[16,28,59,79,188],"memory":[17],"space":[18],"at":[19],"inference":[20,68],"time.":[21],"Due":[22],"to":[23,37,55,93,96,107,109,120,168,175,183],"the":[24,57,77,99,136,140,184],"increase":[25],"in":[26,147],"size":[27,58],"deep":[29,60],"learning":[30],"models,":[31],"it":[32],"is":[33],"becoming":[34],"very":[35],"difficult":[36,95],"consider":[38],"training":[39,114],"and":[40,74,144,150,179],"using":[41,98,165],"on":[45,83,139],"edge":[46,84],"devices":[47],"such":[48],"smartphones.":[50],"Binary":[51],"promise":[54],"reduce":[56],"network":[62],"models":[63,82],"well":[65],"increasing":[67],"speed":[69],"while":[70],"decreasing":[71],"energy":[72],"consumption":[73],"so":[75],"allow":[76],"deployment":[78],"more":[80],"powerful":[81],"devices.":[85],"However,":[86],"binary":[87,110,151,157],"still":[91],"proven":[92],"be":[94,163,173],"train":[97],"backpropagation":[100,121,137,169],"based":[101],"gradient":[102],"descent":[103],"scheme.":[104],"We":[105,127],"propose":[106],"adapt":[108],"two":[113],"algorithms":[115,167],"considered":[116],"promising":[118],"alternatives":[119],"but":[122,170],"for":[123,132],"continuous":[124,149],"networks.":[126],"provide":[128],"experimental":[129],"comparative":[130],"results":[131,154],"image":[133],"classification":[134],"including":[135],"baseline":[138],"MNIST,":[141],"Fashion":[142],"MNIST":[143],"CIFAR-10":[145],"datasets":[146],"both":[148],"settings.":[152],"The":[153],"demonstrate":[155],"can":[160,171],"not":[161],"only":[162],"alternative":[166],"also":[172],"shown":[174],"lead":[176],"better":[177],"performance":[178],"a":[180],"higher":[181],"tolerance":[182],"presence":[185],"or":[186],"absence":[187],"batch":[189],"normalization":[190],"layers.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}