{"id":"https://openalex.org/W3186222744","doi":"https://doi.org/10.1109/tvlsi.2021.3097341","title":"Dynamic Block-Wise Local Learning Algorithm for Efficient Neural Network Training","display_name":"Dynamic Block-Wise Local Learning Algorithm for Efficient Neural Network Training","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3186222744","doi":"https://doi.org/10.1109/tvlsi.2021.3097341","mag":"3186222744"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2021.3097341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3097341","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-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/A5103089962","display_name":"Gwangho Lee","orcid":"https://orcid.org/0000-0001-9977-6121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gwangho Lee","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-9977-6121","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698555","display_name":"Sunwoo Lee","orcid":"https://orcid.org/0000-0001-7760-0168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunwoo Lee","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7760-0168","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053248335","display_name":"Dongsuk Jeon","orcid":"https://orcid.org/0000-0002-0395-8076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsuk Jeon","raw_affiliation_strings":["Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0395-8076","affiliations":[{"raw_affiliation_string":"Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07514978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"9","first_page":"1680","last_page":"1684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"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/backpropagation","display_name":"Backpropagation","score":0.9146480560302734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797850489616394},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7451705932617188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6842487454414368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5355576872825623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4776507616043091},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47630584239959717},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47213679552078247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3265102803707123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08738604187965393}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9146480560302734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797850489616394},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7451705932617188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6842487454414368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5355576872825623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4776507616043091},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47630584239959717},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47213679552078247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3265102803707123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08738604187965393},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2021.3097341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3097341","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2351560784","display_name":null,"funder_award_id":"NRF-2019R1C1C1004927","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4360669709","display_name":null,"funder_award_id":"NRF-2021M3F3A2A01037633","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2024122052","https://openalex.org/W2160654481","https://openalex.org/W2164586147","https://openalex.org/W2737740651","https://openalex.org/W2799069271","https://openalex.org/W2812009592","https://openalex.org/W2911586496","https://openalex.org/W2912855321","https://openalex.org/W2952448932","https://openalex.org/W2952857865","https://openalex.org/W2963047948","https://openalex.org/W2963140169","https://openalex.org/W2963373778","https://openalex.org/W2963684275","https://openalex.org/W2964113612","https://openalex.org/W2964319207","https://openalex.org/W3009411039","https://openalex.org/W3035172409","https://openalex.org/W3093701126","https://openalex.org/W3097692861","https://openalex.org/W3133823884","https://openalex.org/W3135859967","https://openalex.org/W4297797035","https://openalex.org/W6726238325","https://openalex.org/W6741529945","https://openalex.org/W6748424917","https://openalex.org/W6750269818","https://openalex.org/W6753115359","https://openalex.org/W6757376125","https://openalex.org/W6759063983","https://openalex.org/W6765112505","https://openalex.org/W6785718345","https://openalex.org/W6792046235"],"related_works":["https://openalex.org/W4239286941","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W1868434454","https://openalex.org/W4366984740","https://openalex.org/W2894173309","https://openalex.org/W4387932263","https://openalex.org/W2157746493","https://openalex.org/W2371065793"],"abstract_inverted_index":{"In":[0,85,129],"the":[1,4,8,11,16,20,30,53,80,140,157,160],"backpropagation":[2,56,161],"algorithm,":[3],"error":[5,44,58],"calculated":[6],"from":[7],"output":[9],"of":[10,22,57,82,159],"neural":[12],"network":[13],"should":[14],"backpropagate":[15],"layers":[17,110],"to":[18,28,174,179],"update":[19],"weights":[21],"each":[23],"layer,":[24],"making":[25],"it":[26],"difficult":[27],"parallelize":[29],"training":[31,103],"process":[32],"and":[33,78,114,135,142,166,176],"requiring":[34],"frequent":[35],"off-chip":[36,167],"memory":[37,168],"access.":[38],"Local":[39],"learning":[40,92,117],"algorithms":[41],"locally":[42],"generate":[43],"signals":[45],"which":[46,72],"are":[47],"used":[48],"for":[49,55,69],"weight":[50],"updates,":[51],"removing":[52],"need":[54],"signals.":[59],"However,":[60],"prior":[61],"works":[62],"rely":[63],"on":[64,118,139],"large,":[65],"complex":[66],"auxiliary":[67,153],"networks":[68],"reliable":[70],"training,":[71],"results":[73],"in":[74],"large":[75],"computational":[76,97],"overhead":[77],"undermines":[79],"advantages":[81],"local":[83,91,116],"learning.":[84],"this":[86],"work,":[87],"we":[88],"propose":[89],"a":[90,112,119,147],"algorithm":[93,106],"that":[94],"significantly":[95],"reduces":[96],"complexity":[98],"as":[99,101,152],"well":[100],"improves":[102],"performance.":[104],"Our":[105],"combines":[107],"multiple":[108],"consecutive":[109],"into":[111],"block":[113,125],"performs":[115],"block-by-block":[120],"basis,":[121],"while":[122],"dynamically":[123],"changing":[124],"boundaries":[126],"during":[127],"training.":[128],"experiments,":[130],"our":[131],"approach":[132],"achieves":[133],"95.68%":[134],"79.42%":[136],"test":[137],"accuracy":[138],"CIFAR-10":[141],"CIFAR-100":[143],"datasets,":[144],"respectively,":[145],"using":[146],"small":[148],"fully":[149],"connected":[150],"layer":[151],"networks,":[154],"closely":[155],"matching":[156],"performance":[158],"algorithm.":[162],"Multiply-accumulate":[163],"(MAC)":[164],"operations":[165],"access":[169],"also":[170],"reduce":[171],"by":[172],"up":[173],"15%":[175],"81%":[177],"compared":[178],"backpropagation.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}