{"id":"https://openalex.org/W2062227835","doi":"https://doi.org/10.1109/icassp.2013.6639346","title":"Improving deep neural networks for LVCSR using rectified linear units and dropout","display_name":"Improving deep neural networks for LVCSR using rectified linear units and dropout","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2062227835","doi":"https://doi.org/10.1109/icassp.2013.6639346","mag":"2062227835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5047062711","display_name":"George E. Dahl","orcid":"https://orcid.org/0000-0002-0083-844X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George E. Dahl","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey E. Hinton","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1283,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8609","last_page":"8613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8356914520263672},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.795479416847229},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.613013505935669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6116916537284851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5823184847831726},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.5451206564903259},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4925995469093323},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4914354085922241},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4576396942138672},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45530810952186584},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4389888346195221},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43650031089782715},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4309545159339905},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4149004817008972},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41376256942749023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4065704345703125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3278101682662964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356914520263672},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.795479416847229},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.613013505935669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6116916537284851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823184847831726},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.5451206564903259},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4925995469093323},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4914354085922241},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4576396942138672},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45530810952186584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4389888346195221},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43650031089782715},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4309545159339905},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4149004817008972},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41376256942749023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4065704345703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3278101682662964},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.9809","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.9809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~gdahl/papers/reluDropoutBN_icassp2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W137106866","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1993882792","https://openalex.org/W2025768430","https://openalex.org/W2076794394","https://openalex.org/W2105099419","https://openalex.org/W2131241448","https://openalex.org/W2132037657","https://openalex.org/W2147768505","https://openalex.org/W2155117693","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2184045248","https://openalex.org/W2403195671","https://openalex.org/W2546302380","https://openalex.org/W2618530766","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6678911119","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W1520030019","https://openalex.org/W2071654592","https://openalex.org/W3104477175","https://openalex.org/W2088157920","https://openalex.org/W4283785902","https://openalex.org/W4313324256","https://openalex.org/W2019022049"],"abstract_inverted_index":{"Recently,":[0],"pre-trained":[1],"deep":[2,83,151],"neural":[3,27,79,84,152],"networks":[4,108,153],"(DNNs)":[5],"have":[6,29,115],"outperformed":[7],"traditional":[8],"acoustic":[9,86],"models":[10,15,87],"based":[11],"on":[12,17,34,71,142],"Gaussian":[13],"mixture":[14],"(GMMs)":[16],"a":[18,40,52,72,94,143,169,176,181],"variety":[19],"of":[20,54],"large":[21,89],"vocabulary":[22,90],"speech":[23,91],"recognition":[24,75,92],"benchmarks.":[25],"Deep":[26],"nets":[28],"also":[30,68,133],"achieved":[31],"excellent":[32],"results":[33,191],"various":[35],"computer":[36,120],"vision":[37,121],"tasks":[38,122],"using":[39,77,154,197],"random":[41],"\u201cdropout\u201d":[42],"procedure":[43],"that":[44,149],"drastically":[45],"improves":[46],"generalization":[47],"error":[48],"by":[49],"randomly":[50],"omitting":[51],"fraction":[53],"the":[55],"hidden":[56],"units":[57],"in":[58],"all":[59],"layers.":[60],"Since":[61],"dropout":[62,99,158],"helps":[63],"avoid":[64],"over-fitting,":[65],"it":[66],"has":[67],"been":[69,116],"successful":[70,118],"small-scale":[73],"phone":[74],"task":[76,148],"larger":[78],"nets.":[80],"However,":[81],"training":[82,105,162],"net":[85],"for":[88,119],"takes":[93],"very":[95],"long":[96],"time":[97],"and":[98,123,175],"is":[100],"likely":[101],"to":[102,126,188],"only":[103],"increase":[104],"time.":[106],"Neural":[107],"with":[109,157,172,192],"rectified":[110],"linear":[111],"unit":[112],"(ReLU)":[113],"non-linearities":[114],"highly":[117],"proved":[124],"faster":[125],"train":[127],"than":[128],"standard":[129],"sigmoid":[130,173],"units,":[131,174],"sometimes":[132],"improving":[134],"discriminative":[135],"performance.":[136],"In":[137],"this":[138],"work,":[139],"we":[140],"show":[141],"50-hour":[144],"English":[145],"Broadcast":[146],"News":[147],"modified":[150],"ReLUs":[155],"trained":[156,171],"during":[159],"frame":[160],"level":[161],"provide":[163],"an":[164],"4.2%":[165],"relative":[166,178],"improvement":[167,179],"over":[168,180],"DNN":[170],"14.4%":[177],"strong":[182],"GMM/HMM":[183],"system.":[184],"We":[185],"were":[186],"able":[187],"obtain":[189],"our":[190],"minimal":[193],"human":[194],"hyper-parameter":[195],"tuning":[196],"publicly":[198],"available":[199],"Bayesian":[200],"optimization":[201],"code.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":72},{"year":2022,"cited_by_count":110},{"year":2021,"cited_by_count":178},{"year":2020,"cited_by_count":209},{"year":2019,"cited_by_count":177},{"year":2018,"cited_by_count":137},{"year":2017,"cited_by_count":87},{"year":2016,"cited_by_count":94},{"year":2015,"cited_by_count":79},{"year":2014,"cited_by_count":58},{"year":2013,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}