{"id":"https://openalex.org/W3005273712","doi":"https://doi.org/10.1109/pacrim47961.2019.8985122","title":"Functionally-Predefined Kernel: a Way to Reduce CNN Computation","display_name":"Functionally-Predefined Kernel: a Way to Reduce CNN Computation","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W3005273712","doi":"https://doi.org/10.1109/pacrim47961.2019.8985122","mag":"3005273712"},"language":"en","primary_location":{"id":"doi:10.1109/pacrim47961.2019.8985122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","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/A5008234687","display_name":"Yuta INOUCHI","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta INOUCHI","raw_affiliation_strings":["Nagoya Institute of Technology,Gokiso, Showa,Nagoya,Japan","Gokiso, Showa, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Gokiso, Showa,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Gokiso, Showa, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049618522","display_name":"Hayato Yamaki","orcid":"https://orcid.org/0000-0002-2521-430X"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato YAMAKI","raw_affiliation_strings":["The University of Electro-Communications,Chofu, Tokyo,Japan","The University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Chofu, Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"The University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047490989","display_name":"Shinobu Miwa","orcid":"https://orcid.org/0000-0003-0315-3216"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinobu MIWA","raw_affiliation_strings":["The University of Electro-Communications,Chofu, Tokyo,Japan","The University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Chofu, Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"The University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019701702","display_name":"Tomoaki Tsumura","orcid":"https://orcid.org/0000-0003-2004-5284"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki TSUMURA","raw_affiliation_strings":["Nagoya Institute of Technology,Gokiso, Showa,Nagoya,Japan","Gokiso, Showa, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Gokiso, Showa,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Gokiso, Showa, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2019","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8063289523124695},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7795649766921997},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7290991544723511},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7195711135864258},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7044728994369507},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.64202880859375},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.6407425403594971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.573016345500946},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5473026633262634},{"id":"https://openalex.org/keywords/computational-resource","display_name":"Computational resource","score":0.515182375907898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47987881302833557},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4285953640937805},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3519572615623474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2834039628505707},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26987341046333313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07360157370567322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063289523124695},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7795649766921997},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7290991544723511},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7195711135864258},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7044728994369507},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.64202880859375},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.6407425403594971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573016345500946},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5473026633262634},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.515182375907898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47987881302833557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4285953640937805},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3519572615623474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2834039628505707},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26987341046333313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07360157370567322},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pacrim47961.2019.8985122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","raw_type":"proceedings-article"},{"id":"mag:3049493913","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002277049165910","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2812187994","display_name":"An Accuracy-Adaptive  Approximate Computing Platform","funder_award_id":"17K19971","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W117943111","https://openalex.org/W1686810756","https://openalex.org/W1915485278","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2152839228","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2291160084","https://openalex.org/W2300242332","https://openalex.org/W2513491952","https://openalex.org/W2778776255","https://openalex.org/W2799131456","https://openalex.org/W2962988160","https://openalex.org/W2963551763","https://openalex.org/W2964154897","https://openalex.org/W3118608800","https://openalex.org/W6604815279","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6685627644","https://openalex.org/W6696798448","https://openalex.org/W6698200048"],"related_works":["https://openalex.org/W2229588459","https://openalex.org/W2374430960","https://openalex.org/W2375485824","https://openalex.org/W4235807378","https://openalex.org/W120571988","https://openalex.org/W4249702239","https://openalex.org/W2742629360","https://openalex.org/W1512399864","https://openalex.org/W4389768689","https://openalex.org/W2047754121"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"achieved":[5],"high":[6,164],"classification":[7],"accuracy":[8,23,85,141],"in":[9,65],"image":[10],"recognition,":[11],"and":[12,35,105,159],"now,":[13],"they":[14],"are":[15,47],"widely":[16],"used":[17],"for":[18,40,55,102,117],"numerous":[19],"applications.":[20],"For":[21],"higher":[22],"or":[24],"more":[25],"advanced":[26],"applications,":[27],"CNNs":[28,46,80],"need":[29],"to":[30,61,74,97,112,129,166],"consume":[31],"tremendous":[32],"computational":[33,43,58,77,100,115],"resources":[34],"time.":[36],"Hence,":[37],"many":[38,52,152],"studies":[39],"reducing":[41,56],"the":[42,57,76,83,99,107,114,125,156],"cost":[44,59,78,101,116],"of":[45,79,109,127],"actively":[48],"being":[49],"conducted.":[50],"However,":[51],"previous":[53],"methods":[54],"lead":[60],"a":[62,72,92],"non-negligible":[63],"loss":[64],"output":[66,84],"accuracy.":[67],"Therefore,":[68],"it":[69],"is":[70],"still":[71],"challenge":[73],"reduce":[75,98,113],"with":[81,155],"keeping":[82],"high.":[86],"In":[87,143],"this":[88],"paper,":[89],"we":[90,145],"propose":[91],"novel":[93],"concept":[94],"\"Functionally-Predefined":[95],"Kernel\"":[96],"CNN":[103,118,167],"training":[104],"discuss":[106],"potential":[108],"computation":[110,160],"reuse":[111],"inference.":[119],"Our":[120],"experimental":[121],"results":[122],"show":[123],"that":[124,147],"number":[126],"parameters":[128],"be":[130,133],"trained":[131],"can":[132],"significantly":[134],"reduced":[135],"by":[136],"utilizing":[137],"Functionally-Predefined":[138],"Kernels":[139],"without":[140],"loss.":[142],"addition,":[144],"revealed":[146],"CNN's":[148],"inference":[149],"process":[150],"includes":[151],"convolution":[153],"operations":[154],"same":[157],"inputs":[158],"reuse,":[161],"therefore,":[162],"has":[163],"affinity":[165],"computation.":[168]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}