{"id":"https://openalex.org/W2521284735","doi":"https://doi.org/10.1109/cybconf.2017.7985811","title":"SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks","display_name":"SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2521284735","doi":"https://doi.org/10.1109/cybconf.2017.7985811","mag":"2521284735"},"language":"en","primary_location":{"id":"doi:10.1109/cybconf.2017.7985811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cybconf.2017.7985811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 3rd IEEE International Conference on Cybernetics (CYBCONF)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1609.06693","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062471396","display_name":"Armen Aghajanyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armen Aghajanyan","raw_affiliation_strings":["Dimensional Mechanics, Bellevue, Washington","[Dimensional Mechanics, Bellevue, Washington]"],"affiliations":[{"raw_affiliation_string":"Dimensional Mechanics, Bellevue, Washington","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"[Dimensional Mechanics, Bellevue, Washington]","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062471396"],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":0.185,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54230476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9986000061035156,"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":0.9986000061035156,"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":0.9980999827384949,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9975000023841858,"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/regularization","display_name":"Regularization (linguistics)","score":0.7906638383865356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6096648573875427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6020247936248779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5097889304161072},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.472549170255661},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.409855455160141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3944157361984253},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32827556133270264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29533493518829346}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7906638383865356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096648573875427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6020247936248779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5097889304161072},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.472549170255661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.409855455160141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944157361984253},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32827556133270264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29533493518829346}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cybconf.2017.7985811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cybconf.2017.7985811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 3rd IEEE International Conference on Cybernetics (CYBCONF)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1609.06693","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.06693","pdf_url":"https://arxiv.org/pdf/1609.06693","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1609.06693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1609.06693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2521284735","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1609.06693","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.06693","pdf_url":"https://arxiv.org/pdf/1609.06693","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2521284735.pdf","grobid_xml":"https://content.openalex.org/works/W2521284735.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1523493493","https://openalex.org/W1836465849","https://openalex.org/W1992204783","https://openalex.org/W2011301426","https://openalex.org/W2144513243","https://openalex.org/W2194775991","https://openalex.org/W2384495648","https://openalex.org/W2949117887","https://openalex.org/W3035258717","https://openalex.org/W6600213771","https://openalex.org/W6600284362","https://openalex.org/W6625122095","https://openalex.org/W6638523607","https://openalex.org/W6674330103","https://openalex.org/W6674385629","https://openalex.org/W6678280073","https://openalex.org/W6681151457","https://openalex.org/W6681588610","https://openalex.org/W6687483927","https://openalex.org/W6703116779","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3152522792","https://openalex.org/W2612930941","https://openalex.org/W3041964843","https://openalex.org/W1535357773","https://openalex.org/W3126459120","https://openalex.org/W1946718419","https://openalex.org/W2792024940","https://openalex.org/W2787972513","https://openalex.org/W2810268014","https://openalex.org/W2963828549","https://openalex.org/W105745955","https://openalex.org/W3202354099","https://openalex.org/W2139252659","https://openalex.org/W2962860223","https://openalex.org/W2765904043","https://openalex.org/W3200958619","https://openalex.org/W2106129230","https://openalex.org/W3013428918","https://openalex.org/W2893252518","https://openalex.org/W2809055160"],"abstract_inverted_index":{"Deep":[0],"neural":[1,161],"networks":[2],"are":[3],"learning":[4,68,98,149],"models":[5,42,87],"with":[6],"a":[7,60,71,111,128],"very":[8],"high":[9],"capacity":[10,38,80,139],"and":[11,24,118,143],"therefore":[12],"prone":[13],"to":[14,29,154],"over-":[15,75],"fitting.":[16],"Many":[17],"regularization":[18,64,129,152],"techniques":[19],"such":[20],"as":[21,131,133],"Dropout,":[22],"DropConnect,":[23],"weight":[25],"decay":[26],"all":[27],"attempt":[28],"solve":[30],"the":[31,37,67,79,82,97,102,105,115,123,138,141,145,148],"problem":[32,69],"of":[33,39,63,81,92,104,108,114,122,140,147],"over-fitting":[34],"by":[35],"reducing":[36,137],"their":[40],"respective":[41],"(Srivastava":[43],"et":[44,48],"al.,":[45,49],"2014),":[46],"(Wan":[47],"2013),":[50],"(Krogh":[51],"&":[52],"Hertz,":[53],"1992).":[54],"In":[55],"this":[56],"paper":[57],"we":[58,126],"introduce":[59],"new":[61],"form":[62],"that":[65,73,86],"guides":[66],"in":[70,89,159],"way":[72],"reduces":[74],"fitting":[76],"without":[77,135],"sacrificing":[78],"model.":[83],"The":[84],"mistakes":[85],"make":[88],"early":[90],"stages":[91],"training":[93,109],"carry":[94],"information":[95],"about":[96],"problem.":[99,150],"By":[100],"adjusting":[101],"labels":[103],"current":[106],"epoch":[107],"through":[110],"weighted":[112],"average":[113,121],"real":[116],"labels,":[117],"an":[119,156],"exponential":[120],"past":[124],"soft-targets":[125],"achieved":[127],"scheme":[130],"powerful":[132],"Dropout":[134],"necessarily":[136],"model,":[142],"simplified":[144],"complexity":[146],"SoftTarget":[151],"proved":[153],"be":[155],"effective":[157],"tool":[158],"various":[160],"network":[162],"architectures.":[163]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}