{"id":"https://openalex.org/W2802497406","doi":"https://doi.org/10.1109/iscas.2018.8351094","title":"Sparseness Ratio Allocation and Neuron Re-pruning for Neural Networks Compression","display_name":"Sparseness Ratio Allocation and Neuron Re-pruning for Neural Networks Compression","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2802497406","doi":"https://doi.org/10.1109/iscas.2018.8351094","mag":"2802497406"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2018.8351094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5101747895","display_name":"Li Guo","orcid":"https://orcid.org/0000-0003-0650-4229"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Li Guo","raw_affiliation_strings":["Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110827563","display_name":"Dajiang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dajiang Zhou","raw_affiliation_strings":["Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021863826","display_name":"Jinjia Zhou","orcid":"https://orcid.org/0000-0002-5078-0522"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinjia Zhou","raw_affiliation_strings":["Graduate School of Science and Engineering, Hosei University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101598322","display_name":"Shinji Kimura","orcid":"https://orcid.org/0000-0002-9475-6858"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Kimura","raw_affiliation_strings":["Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Production, and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101747895"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03917522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8216129541397095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8073924779891968},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.6463010907173157},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5693541765213013},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5252599120140076},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5047770738601685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46898892521858215},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.44179508090019226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3245583474636078},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.14618957042694092}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8216129541397095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073924779891968},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.6463010907173157},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5693541765213013},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5252599120140076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5047770738601685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46898892521858215},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.44179508090019226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3245583474636078},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.14618957042694092},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2018.8351094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2018.8351094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2155893237","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2554302513","https://openalex.org/W2591982329","https://openalex.org/W2619444510","https://openalex.org/W2707890836","https://openalex.org/W2919115771","https://openalex.org/W2963287528","https://openalex.org/W2963674932","https://openalex.org/W2964299589","https://openalex.org/W6638632666","https://openalex.org/W6677580257","https://openalex.org/W6739917289"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4280599700","https://openalex.org/W3183570023","https://openalex.org/W4382323155","https://openalex.org/W2016508734","https://openalex.org/W4287067436","https://openalex.org/W3188310744"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4,148],"rapidly":[5],"gaining":[6],"popularity":[7],"in":[8,14,34,102],"artificial":[9],"intelligence":[10],"applications":[11],"and":[12,29,64,143],"employed":[13],"mobile":[15,35],"devices.":[16,36],"However,":[17],"this":[18,39],"is":[19,45,77,88],"challenging":[20],"because":[21],"of":[22,27,55,105,117],"the":[23,30,42,59,65,91,98,103,107,119],"high":[24],"computational":[25,141],"complexity":[26],"CNNs":[28],"limited":[31],"hardware":[32],"resource":[33],"To":[37,69],"address":[38],"issue,":[40],"compressing":[41],"CNN":[43],"model":[44,56],"an":[46],"efficient":[47],"solution.":[48],"This":[49],"work":[50],"presents":[51],"a":[52,71,113],"new":[53],"framework":[54,121],"compression,":[57],"with":[58,112],"sparseness":[60],"ratio":[61],"allocation":[62],"(SRA)":[63],"neuron":[66],"re-pruning":[67],"(NRP).":[68],"achieve":[70],"higher":[72],"overall":[73],"spareness":[74],"ratio,":[75],"SRA":[76],"exploited":[78],"to":[79,95,137],"determine":[80],"pruned":[81],"weight":[82,93],"percentage":[83],"for":[84],"each":[85],"layer.":[86],"NRP":[87],"performed":[89],"after":[90],"usual":[92],"pruning":[94],"further":[96],"reduce":[97],"relative":[99,136],"redundant":[100],"neurons":[101],"meanwhile":[104],"guaranteeing":[106],"accuracy.":[108],"From":[109],"experimental":[110],"results,":[111],"slight":[114],"accuracy":[115],"drop":[116],"0.1%,":[118],"proposed":[120],"achieves":[122],"149.3\u00d7":[123],"compression":[124],"on":[125],"lenet-5.":[126],"The":[127],"storage":[128],"size":[129],"can":[130],"be":[131],"reduced":[132],"by":[133],"about":[134],"50%":[135],"previous":[138],"works.":[139],"8-45.2%":[140],"energy":[142,147],"11.5-48.2%":[144],"memory":[145],"traffic":[146],"saved.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}