{"id":"https://openalex.org/W2965011261","doi":"https://doi.org/10.1007/s12559-019-09667-7","title":"How Deep Should be the Depth of Convolutional Neural Networks: a Backyard Dog Case Study","display_name":"How Deep Should be the Depth of Convolutional Neural Networks: a Backyard Dog Case Study","publication_year":2019,"publication_date":"2019-08-07","ids":{"openalex":"https://openalex.org/W2965011261","doi":"https://doi.org/10.1007/s12559-019-09667-7","mag":"2965011261"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-019-09667-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-019-09667-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-019-09667-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-019-09667-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058069510","display_name":"Alexander N. Gorban","orcid":"https://orcid.org/0000-0001-6224-1430"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]},{"id":"https://openalex.org/I79563041","display_name":"N. I. Lobachevsky State University of Nizhny Novgorod","ror":"https://ror.org/01bb1zm18","country_code":"RU","type":"education","lineage":["https://openalex.org/I79563041"]}],"countries":["GB","RU"],"is_corresponding":true,"raw_author_name":"Alexander N. Gorban","raw_affiliation_strings":["Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","University of Leicester, Leicester, LE1 7RH, UK"],"affiliations":[{"raw_affiliation_string":"Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","institution_ids":["https://openalex.org/I79563041"]},{"raw_affiliation_string":"University of Leicester, Leicester, LE1 7RH, UK","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069472885","display_name":"Evgeny M. Mirkes","orcid":"https://orcid.org/0000-0003-1474-1734"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]},{"id":"https://openalex.org/I79563041","display_name":"N. I. Lobachevsky State University of Nizhny Novgorod","ror":"https://ror.org/01bb1zm18","country_code":"RU","type":"education","lineage":["https://openalex.org/I79563041"]}],"countries":["GB","RU"],"is_corresponding":false,"raw_author_name":"Evgeny M. Mirkes","raw_affiliation_strings":["Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","University of Leicester, Leicester, LE1 7RH, UK"],"affiliations":[{"raw_affiliation_string":"Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","institution_ids":["https://openalex.org/I79563041"]},{"raw_affiliation_string":"University of Leicester, Leicester, LE1 7RH, UK","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052143104","display_name":"Ivan Tyukin","orcid":"https://orcid.org/0000-0002-7359-7966"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]},{"id":"https://openalex.org/I41518628","display_name":"Saint Petersburg State Electrotechnical University","ror":"https://ror.org/023bq8521","country_code":"RU","type":"education","lineage":["https://openalex.org/I41518628"]},{"id":"https://openalex.org/I79563041","display_name":"N. I. Lobachevsky State University of Nizhny Novgorod","ror":"https://ror.org/01bb1zm18","country_code":"RU","type":"education","lineage":["https://openalex.org/I79563041"]}],"countries":["GB","RU"],"is_corresponding":false,"raw_author_name":"Ivan Y. Tyukin","raw_affiliation_strings":["Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","Saint-Petersburg State Electrotechnical University (LETI), Prof. Popova 5, Saint-Petersburg, Russian Federation","University of Leicester, Leicester, LE1 7RH, UK"],"affiliations":[{"raw_affiliation_string":"Lobachevsky State University of Nizhny Novgorod, Prospekt Ganarina 23, Nizhny Novgorod, 603950, Russian Federation","institution_ids":["https://openalex.org/I79563041"]},{"raw_affiliation_string":"Saint-Petersburg State Electrotechnical University (LETI), Prof. Popova 5, Saint-Petersburg, Russian Federation","institution_ids":["https://openalex.org/I41518628"]},{"raw_affiliation_string":"University of Leicester, Leicester, LE1 7RH, UK","institution_ids":["https://openalex.org/I153648349"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058069510"],"corresponding_institution_ids":["https://openalex.org/I153648349","https://openalex.org/I79563041"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":4.5998,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.95866244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"12","issue":"2","first_page":"388","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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/T11448","display_name":"Face recognition and analysis","score":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.794475793838501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6738094687461853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6402254104614258},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4613701105117798}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.794475793838501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6738094687461853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402254104614258},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4613701105117798}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/s12559-019-09667-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-019-09667-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-019-09667-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/1798e3d0-0bc6-4b3c-8aad-9ad08d9af778","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/1798e3d0-0bc6-4b3c-8aad-9ad08d9af778","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gorban, A N, Mirkes, E M & Tyukin, I Y 2020, 'How Deep Should be the Depth of Convolutional Neural Networks : a Backyard Dog Case Study', Cognitive computation, vol. 12, no. 2, pp. 388-397. https://doi.org/10.1007/s12559-019-09667-7","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:figshare.com:article/10204007","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/How_deep_should_be_the_depth_of_convolutional_neural_networks_a_backyard_dog_case_study/10204007","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:figshare.com:article/10208735","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/How_Deep_Should_be_the_Depth_of_Convolutional_Neural_Networks_a_Backyard_Dog_Case_Study/10208735","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/1798e3d0-0bc6-4b3c-8aad-9ad08d9af778","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85070738366&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"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":"Gorban, A N, Mirkes, E M & Tyukin, I Y 2020, 'How Deep Should be the Depth of Convolutional Neural Networks : a Backyard Dog Case Study', Cognitive computation, vol. 12, no. 2, pp. 388-397. https://doi.org/10.1007/s12559-019-09667-7","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:lra.le.ac.uk:2381/45168","is_oa":true,"landing_page_url":"http://hdl.handle.net/2381/45168","pdf_url":null,"source":{"id":"https://openalex.org/S4306402365","display_name":"Leicester Research Archive (University of Leicester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I153648349","host_organization_name":"University of Leicester","host_organization_lineage":["https://openalex.org/I153648349"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1007/s12559-019-09667-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-019-09667-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-019-09667-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8201444629","display_name":null,"funder_award_id":"KTP010522","funder_id":"https://openalex.org/F4320335087","funder_display_name":"Innovate UK"}],"funders":[{"id":"https://openalex.org/F4320335087","display_name":"Innovate UK","ror":"https://ror.org/05ar5fy68"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965011261.pdf","grobid_xml":"https://content.openalex.org/works/W2965011261.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W150692989","https://openalex.org/W170472577","https://openalex.org/W1607296876","https://openalex.org/W1686810756","https://openalex.org/W1998808035","https://openalex.org/W2096733369","https://openalex.org/W2112524621","https://openalex.org/W2145287260","https://openalex.org/W2148252288","https://openalex.org/W2156150815","https://openalex.org/W2163605009","https://openalex.org/W2204202707","https://openalex.org/W2270320612","https://openalex.org/W2279098554","https://openalex.org/W2325939864","https://openalex.org/W2612445135","https://openalex.org/W2747590145","https://openalex.org/W2763318011","https://openalex.org/W2784025535","https://openalex.org/W2884367402","https://openalex.org/W2884716758","https://openalex.org/W2896466118","https://openalex.org/W2911462778","https://openalex.org/W2946704636","https://openalex.org/W2946948417","https://openalex.org/W2952773203","https://openalex.org/W2962835968","https://openalex.org/W3099206234","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W4226493464","https://openalex.org/W3215138031","https://openalex.org/W3133861977","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W2951211570","https://openalex.org/W3103566983"],"abstract_inverted_index":{"The":[0,47,119,184,203,278,305],"work":[1],"concerns":[2],"the":[3,22,38,42,53,56,60,65,92,102,115,145,148,167,201,211,219,232,236,240,247,256,283,299],"problem":[4],"of":[5,44,68,94,110,135,157,166,200,218,244,249,258,292,309,311],"reducing":[6,246],"a":[7,13,26,112,124,132,137,164,170,175,180,197,267,289,324],"pre-trained":[8,274],"deep":[9,73,189,250,275],"neuronal":[10],"network":[11,149,181],"to":[12,58,78,91,101,154,288],"smaller":[14],"network,":[15,126,177],"with":[16],"just":[17],"few":[18],"layers,":[19],"whilst":[20],"retaining":[21],"network\u2019s":[23],"functionality":[24],"on":[25,37,192,210,298],"given":[27],"task.":[28],"In":[29,99,262],"this":[30,263],"particular":[31],"case":[32],"study,":[33],"we":[34,106,178,265],"are":[35],"focusing":[36],"networks":[39,75,315],"developed":[40],"for":[41,271,317],"purposes":[43],"face":[45,103],"recognition.":[46],"proposed":[48,266],"approach":[49],"is":[50,161,205,208,221,242,280,296],"motivated":[51],"by":[52,123],"observation":[54],"that":[55,230,285],"aim":[57],"deliver":[59],"highest":[61],"accuracy":[62],"possible":[63],"in":[64,163,223,231,282],"broadest":[66],"range":[67],"operational":[69,319],"conditions,":[70],"which":[71],"many":[72],"neural":[74,252],"models":[76],"strive":[77],"achieve,":[79],"may":[80],"not":[81,162],"necessarily":[82],"be":[83],"always":[84],"needed,":[85],"desired":[86],"or":[87,96],"even":[88],"achievable":[89],"due":[90],"lack":[93],"data":[95],"technical":[97],"constraints.":[98],"relation":[100],"recognition":[104],"problem,":[105,239],"formulated":[107],"an":[108,152,155,158,187],"example":[109],"such":[111,174],"use":[113,234],"case,":[114,235],"\u2018backyard":[116,120,237],"dog\u2019":[117,238],"problem.":[118],"dog\u2019,":[121],"implemented":[122],"lean":[125,176],"should":[127,140],"correctly":[128],"identify":[129],"members":[130],"from":[131,323],"limited":[133],"group":[134],"individuals,":[136],"\u2018family\u2019,":[138],"and":[139,195,207,295,321,327],"distinguish":[141],"between":[142],"them.":[143],"At":[144],"same":[146],"time,":[147],"must":[150],"produce":[151,173],"alarm":[153],"image":[156],"individual":[159],"who":[160],"member":[165],"family,":[168],"i.e.":[169],"\u2018stranger\u2019.":[171],"To":[172],"propose":[179],"shallowing":[182,272],"algorithm.":[183],"algorithm":[185,204,220],"takes":[186],"existing":[188],"learning":[190,251],"model":[191],"its":[193],"input":[194],"outputs":[196],"shallowed":[198],"version":[199],"model.":[202],"non-iterative":[206,269],"based":[209,297],"advanced":[212,300],"supervised":[213],"principal":[214,302],"component":[215,303],"analysis.":[216,304],"Performance":[217],"assessed":[222],"exhaustive":[224],"numerical":[225],"experiments.":[226],"Our":[227],"experiments":[228],"revealed":[229],"above":[233],"method":[241,270,279,306],"capable":[243],"drastically":[245],"depth":[248],"networks,":[253,294],"albeit":[254],"at":[255],"cost":[257],"mild":[259],"performance":[260],"deterioration.":[261],"work,":[264],"simple":[268],"down":[273],"convolutional":[276],"networks.":[277],"generic":[281],"sense":[284],"it":[286],"applies":[287],"broad":[290],"class":[291],"feed-forward":[293],"supervise":[301],"enables":[307],"generation":[308],"families":[310],"smaller-size":[312],"shallower":[313],"specialized":[314],"tuned":[316],"specific":[318],"conditions":[320],"tasks":[322],"single":[325],"larger":[326],"more":[328],"universal":[329],"legacy":[330],"network.":[331]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}