{"id":"https://openalex.org/W1979482308","doi":"https://doi.org/10.1109/slt.2014.7078567","title":"Annealed dropout training of deep networks","display_name":"Annealed dropout training of deep networks","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1979482308","doi":"https://doi.org/10.1109/slt.2014.7078567","mag":"1979482308"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5088753951","display_name":"Steven J. Rennie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven J. Rennie","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM Thomas J. Watson Res. Center, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM Thomas J. Watson Res. Center, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM Thomas J. Watson Res. Center, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Res. Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088753951"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":10.9942,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98366071,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983000159263611,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.998199999332428,"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/overfitting","display_name":"Overfitting","score":0.896918773651123},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.792411208152771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6836206316947937},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5450518131256104},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5182937979698181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5035697817802429},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.49169617891311646},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.42951348423957825},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4198572337627411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3563309609889984}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.896918773651123},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.792411208152771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836206316947937},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5450518131256104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5182937979698181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5035697817802429},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.49169617891311646},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.42951348423957825},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4198572337627411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3563309609889984},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2014.7078567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.3373","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.3373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/annealed_dropout.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W1524333225","https://openalex.org/W1904365287","https://openalex.org/W2020408662","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2062227835","https://openalex.org/W2096840836","https://openalex.org/W2100923606","https://openalex.org/W2116064496","https://openalex.org/W2120480077","https://openalex.org/W2147800946","https://openalex.org/W2155117693","https://openalex.org/W2161877964","https://openalex.org/W2294059674","https://openalex.org/W2950789693","https://openalex.org/W6601425427","https://openalex.org/W6631362777","https://openalex.org/W6640036494","https://openalex.org/W6674588979","https://openalex.org/W6696761078"],"related_works":["https://openalex.org/W3128220493","https://openalex.org/W4298017035","https://openalex.org/W2792147139","https://openalex.org/W4226354336","https://openalex.org/W3110700750","https://openalex.org/W2998675825","https://openalex.org/W2736804899","https://openalex.org/W2897443685","https://openalex.org/W4307654087","https://openalex.org/W2951100320"],"abstract_inverted_index":{"Recently":[0],"it":[1],"has":[2,128],"been":[3],"shown":[4],"that":[5,66,112,127,156,178,213],"when":[6],"training":[7,33,42,82,121],"neural":[8],"networks":[9,175],"on":[10],"a":[11,21,28,72,117,129],"limited":[12],"amount":[13],"of":[14,24,27,55,81,88,102,110,120,125,133,143,150,173],"data,":[15],"randomly":[16],"zeroing,":[17],"or":[18],"\u201cdropping":[19],"out\u201d":[20],"fixed":[22],"percentage":[23],"the":[25,44,47,53,56,68,79,86,89,108,141,148,151,171],"outputs":[26],"given":[29,118],"layer":[30],"for":[31,204],"each":[32],"case":[34],"can":[35,83],"improve":[36,85],"test":[37],"set":[38],"performance":[39],"significantly.":[40],"Dropout":[41],"discourages":[43],"detectors":[45],"in":[46,140,186,220],"network":[48,57],"from":[49,71,192],"co-adapting,":[50],"which":[51],"limits":[52],"capacity":[54],"and":[58,137,168,183],"prevents":[59],"overfitting.":[60],"In":[61],"this":[62,104,163],"paper":[63],"we":[64],"show":[65],"annealing":[67],"dropout":[69,93,215,226],"rate":[70,223],"high":[73,180,195],"initial":[74],"value":[75],"to":[76,198,217],"zero":[77],"over":[78,98,224],"course":[80],"substantially":[84],"quality":[87],"resulting":[90],"model.":[91],"As":[92],"(approximately)":[94],"implements":[95],"model":[96,153],"aggregation":[97],"an":[99,123],"exponential":[100],"number":[101,132,142],"networks,":[103],"procedure":[105,165],"effectively":[106],"initializes":[107],"ensemble":[109],"models":[111,126,155],"will":[113],"be":[114],"learned":[115],"during":[116],"iteration":[119],"with":[122,176,194,201],"enemble":[124],"lower":[130],"average":[131,181],"neurons":[134,144,177,207],"per":[135,145],"network,":[136],"higher":[138],"variance":[139,185],"network-which":[146],"regularizes":[147],"structure":[149],"final":[152],"toward":[154],"avoid":[157],"unnecessary":[158],"co-adaptation":[159,205],"between":[160,206],"neurons.":[161],"Importantly,":[162],"regularization":[164],"is":[166],"stochastic,":[167],"so":[169],"promotes":[170],"learning":[172,196],"\u201cbalanced\u201d":[174],"have":[179],"entropy,":[182,188],"low":[184],"their":[187],"by":[189],"smoothly":[190],"transitioning":[191],"\u201cexploration\u201d":[193],"rates":[197],"\u201cfine":[199],"tuning\u201d":[200],"full":[202],"support":[203],"where":[208],"necessary.":[209],"Experimental":[210],"results":[211],"demonstrate":[212],"annealed":[214],"leads":[216],"significant":[218],"reductions":[219],"word":[221],"error":[222],"standard":[225],"training.":[227]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}