{"id":"https://openalex.org/W4389366432","doi":"https://doi.org/10.1145/3628797.3628935","title":"Learning Algorithm for LesserDNN, a DNN with Quantized Weights","display_name":"Learning Algorithm for LesserDNN, a DNN with Quantized Weights","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389366432","doi":"https://doi.org/10.1145/3628797.3628935"},"language":"en","primary_location":{"id":"doi:10.1145/3628797.3628935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628797.3628935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628797.3628935","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3628797.3628935","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015086254","display_name":"Masashi Takemoto","orcid":"https://orcid.org/0000-0002-8978-9460"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Masashi Takemoto","raw_affiliation_strings":["BeatCraft, Inc., Japan"],"affiliations":[{"raw_affiliation_string":"BeatCraft, Inc., Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011906577","display_name":"Y Masuda","orcid":"https://orcid.org/0009-0001-4031-5379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasutake Masuda","raw_affiliation_strings":["BeatCraft, Inc., Japan"],"affiliations":[{"raw_affiliation_string":"BeatCraft, Inc., Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089198708","display_name":"Jingyong Cai","orcid":"https://orcid.org/0000-0002-4765-8155"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jingyong Cai","raw_affiliation_strings":["Tokyo University of Agriculture and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology, Japan","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018654254","display_name":"Hironori Nakajo","orcid":"https://orcid.org/0000-0001-7452-2125"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hironori Nakajo","raw_affiliation_strings":["Tokyo University of Agriculture and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology, Japan","institution_ids":["https://openalex.org/I92614990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015086254"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44411012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9890999794006348,"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":0.9890999794006348,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.987500011920929,"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/T10320","display_name":"Neural Networks and Applications","score":0.9836999773979187,"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":0.7939536571502686},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.7333435416221619},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6645141243934631},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6455780267715454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6149261593818665},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.58104008436203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5586171746253967},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.5575053691864014},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5545823574066162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42760539054870605},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4272410571575165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24113526940345764}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7939536571502686},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.7333435416221619},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6645141243934631},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6455780267715454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149261593818665},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.58104008436203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5586171746253967},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.5575053691864014},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5545823574066162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42760539054870605},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4272410571575165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24113526940345764},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628797.3628935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628797.3628935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628797.3628935","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3628797.3628935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628797.3628935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628797.3628935","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389366432.pdf","grobid_xml":"https://content.openalex.org/works/W4389366432.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2765349067","https://openalex.org/W2903972532"],"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":{"This":[0],"paper":[1],"presents":[2],"LesserDNN,":[3],"a":[4,8,27,125,167,183],"model":[5,181],"that":[6],"uses":[7],"set":[9],"of":[10,113,157],"floating-point":[11],"values":[12],"{-1.0,":[13],"-0.5,":[14],"-0.25,":[15],"-0.125,":[16],"-0.0625,":[17],"0.0625,":[18],"0.125,":[19],"0.25,":[20],"0.5,":[21],"1.0}":[22],"as":[23,53,159],"quantized":[24,44,57,70,106,114,151],"weights,":[25,45,152],"and":[26,116,150,170],"new":[28],"learning":[29,55,122],"algorithm":[30,91,130,149],"for":[31],"the":[32,49,63,76,111,121,146,154],"proposed":[33,129],"model.":[34],"In":[35],"previous":[36],"studies":[37],"on":[38,93,136],"deep":[39],"neural":[40],"networks":[41,135],"(DNNs)":[42],"with":[43,145],"because":[46,174],"DNNs":[47],"employ":[48],"gradient":[50,77,160],"descent":[51,78],"method":[52,79],"their":[54],"algorithm,":[56,120],"weights":[58,71,107,115],"were":[59,143],"applied":[60,81,132],"only":[61],"during":[62,82,108],"inference":[64],"stage.":[65],"Due":[66],"to":[67,133],"differentiability":[68,101],"properties,":[69],"cannot":[72],"be":[73],"used":[74],"when":[75],"is":[80,176],"training.":[83,109],"To":[84],"address":[85],"this":[86,117,180],"issue,":[87],"we":[88],"devised":[89],"an":[90],"based":[92],"simulated":[94,97,118,147],"annealing.":[95],"Since":[96],"annealing":[98],"has":[99,166],"no":[100],"requirements,":[102],"LesserDNN":[103,165],"can":[104],"utilize":[105],"With":[110],"use":[112],"annealing-based":[119,148],"process":[123],"becomes":[124],"combinatorial":[126],"problem.":[127],"The":[128,140],"was":[131],"train":[134],"MNIST":[137],"handwriting":[138],"datasets.":[139],"tested":[141],"models":[142],"trained":[144],"achieving":[153],"same":[155],"level":[156],"accuracy":[158],"descent-based":[161],"comparison":[162],"methods.":[163],"Thus,":[164],"simple":[168],"design":[169],"small":[171],"implementation":[172],"scale":[173],"backpropagation":[175],"not":[177],"applied.":[178],"Moreover,":[179],"achieves":[182],"high":[184],"accuracy.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}