{"id":"https://openalex.org/W3210270067","doi":"https://doi.org/10.1109/dsaa53316.2021.9564119","title":"Overfitting Measurement of Deep Neural Networks Using No Data","display_name":"Overfitting Measurement of Deep Neural Networks Using No Data","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3210270067","doi":"https://doi.org/10.1109/dsaa53316.2021.9564119","mag":"3210270067"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa53316.2021.9564119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa53316.2021.9564119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5061291904","display_name":"Satoru Watanabe","orcid":"https://orcid.org/0000-0001-5329-9278"},"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":"Satoru Watanabe","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031456992","display_name":"Hayato Yamana","orcid":"https://orcid.org/0000-0001-7542-4826"},"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":"Hayato Yamana","raw_affiliation_strings":["Faculty of Science and Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061291904"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.3317,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83676823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11266","display_name":"Neuroinflammation and Neurodegeneration Mechanisms","score":0.9434999823570251,"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/overfitting","display_name":"Overfitting","score":0.9957848191261292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302267551422119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6260873079299927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.577596127986908},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5361788868904114},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5124204754829407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49115702509880066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46654391288757324},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.46394893527030945},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43629834055900574},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4152563512325287}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9957848191261292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302267551422119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6260873079299927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.577596127986908},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5361788868904114},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5124204754829407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49115702509880066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46654391288757324},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.46394893527030945},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43629834055900574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4152563512325287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa53316.2021.9564119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa53316.2021.9564119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W107886322","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1686810756","https://openalex.org/W2017360110","https://openalex.org/W2095705004","https://openalex.org/W2096736341","https://openalex.org/W2124511088","https://openalex.org/W2135610119","https://openalex.org/W2149933564","https://openalex.org/W2183954497","https://openalex.org/W2195388612","https://openalex.org/W2328525712","https://openalex.org/W2335728318","https://openalex.org/W2424211690","https://openalex.org/W2551176409","https://openalex.org/W2768955764","https://openalex.org/W2785661498","https://openalex.org/W2905600194","https://openalex.org/W2956875312","https://openalex.org/W2963175648","https://openalex.org/W2970699417","https://openalex.org/W3003257820","https://openalex.org/W3035004544","https://openalex.org/W3035347989","https://openalex.org/W3089808853","https://openalex.org/W3098455240","https://openalex.org/W3099475723","https://openalex.org/W3103145119","https://openalex.org/W3105416979","https://openalex.org/W3118608800","https://openalex.org/W3132523972","https://openalex.org/W3140579943","https://openalex.org/W3179551771","https://openalex.org/W4211095002","https://openalex.org/W4285719527","https://openalex.org/W4288419306","https://openalex.org/W4299518610","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6682132143","https://openalex.org/W6757782233","https://openalex.org/W6760560836","https://openalex.org/W6776408585","https://openalex.org/W6779410803","https://openalex.org/W6783551917","https://openalex.org/W6790743421"],"related_works":["https://openalex.org/W3128220493","https://openalex.org/W3118394139","https://openalex.org/W3110700750","https://openalex.org/W2767651786","https://openalex.org/W3081496756","https://openalex.org/W2786764570","https://openalex.org/W2962684187","https://openalex.org/W2728804654","https://openalex.org/W3033000596","https://openalex.org/W4287760619"],"abstract_inverted_index":{"Overfitting":[0,9],"reduces":[1],"the":[2,15,25,44,63,86,102,112,137,160,166,170,194,198,213,220,235],"generalizability":[3],"of":[4,19,31,95,101,115,125,139,163,197,215,217],"deep":[5],"neural":[6,190],"networks":[7,191],"(DNNs).":[8],"is":[10,35,98],"generally":[11],"detected":[12,109],"by":[13,84,110],"comparing":[14],"accuracies":[16],"and":[17,21,34,48,106,130,165,179,201,237],"losses":[18],"training":[20,32,47,129,178,221,236],"validation":[22],"data;":[23],"however,":[24],"detection":[26],"method":[27,121,135,153],"requires":[28,176],"vast":[29],"amounts":[30],"data":[33,41,181,204],"not":[36],"always":[37],"effective":[38],"for":[39,193],"forthcoming":[40,49],"due":[42],"to":[43,57,122,182,188,219,229],"heterogeneity":[45],"between":[46],"data.":[50,132,239],"The":[51,133,147,206],"dropout":[52],"technique":[53,79],"has":[54,74],"been":[55,75],"employed":[56],"prevent":[58],"DNNs":[59,66,81,126,158,218,232],"from":[60,82],"overfitting,":[61],"where":[62],"neurons":[64,105,142],"in":[65],"are":[67],"invalidated":[68],"randomly":[69],"during":[70],"their":[71],"training.":[72],"It":[73],"hypothesized":[76],"that":[77,93,210,225],"this":[78],"prevents":[80],"overfitting":[83,94,124,150,216],"restraining":[85],"co-adaptions":[87,103,140,171],"among":[88,104,141,172],"neurons.":[89,173],"This":[90],"hypothesis":[91],"implies":[92],"a":[96,99,120],"DNN":[97],"result":[100],"can":[107],"be":[108],"investigating":[111],"inner":[113],"representation":[114],"DNNs.":[116],"Thus,":[117,174],"we":[118],"propose":[119],"detect":[123],"using":[127,143,159],"no":[128,177],"test":[131,180,238],"proposed":[134,148],"measures":[136],"degree":[138,214],"persistent":[144],"homology":[145],"(PH).":[146],"PH-based":[149],"measure":[151,183],"(PHOM)":[152],"constructs":[154],"clique":[155],"complexes":[156],"on":[157],"trained":[161,192],"parameters":[162],"DNNs,":[164],"one-dimensional":[167],"PH":[168],"investigates":[169],"PHOM":[175,187,211,226],"overfitting.":[184],"We":[185],"applied":[186],"convolutional":[189],"classification":[195],"problems":[196],"CIFAR-10,":[199],"SVHN,":[200],"Tiny":[202],"ImageNet":[203],"sets.":[205],"experimental":[207],"results":[208],"demonstrate":[209],"reveals":[212],"data,":[222],"which":[223],"suggests":[224],"enables":[227],"us":[228],"filter":[230],"overfitted":[231],"without":[233],"requiring":[234]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}