{"id":"https://openalex.org/W2071709160","doi":"https://doi.org/10.1162/neco_a_00311","title":"An Efficient Learning Procedure for Deep Boltzmann Machines","display_name":"An Efficient Learning Procedure for Deep Boltzmann Machines","publication_year":2012,"publication_date":"2012-04-17","ids":{"openalex":"https://openalex.org/W2071709160","doi":"https://doi.org/10.1162/neco_a_00311","mag":"2071709160","pmid":"https://pubmed.ncbi.nlm.nih.gov/22509963"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_00311","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00311","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/57474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"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":"Ruslan Salakhutdinov","raw_affiliation_strings":["Department of Statistics, University of Toronto, Toronto, Ontario M5S 3G3, Canada","Department of Statistics , University of Toronto , Toronto, Ontario, M5S 3G3, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Toronto, Toronto, Ontario M5S 3G3, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Statistics , University of Toronto , Toronto, Ontario, M5S 3G3, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"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 Hinton","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Ontario M5S 3G3, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Ontario M5S 3G3, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":23.9679,"has_fulltext":false,"cited_by_count":490,"citation_normalized_percentile":{"value":0.99652968,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"24","issue":"8","first_page":"1967","last_page":"2006"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9911999702453613,"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/boltzmann-machine","display_name":"Boltzmann machine","score":0.9482247829437256},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.759202241897583},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7216644883155823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6336256861686707},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5679031610488892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5512555241584778},{"id":"https://openalex.org/keywords/boltzmann-constant","display_name":"Boltzmann constant","score":0.5037023425102234},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.4854913055896759},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48000210523605347},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4697437882423401},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4666692316532135},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4335760176181793},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42512083053588867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4210435748100281},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35441386699676514},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10653609037399292}],"concepts":[{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.9482247829437256},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.759202241897583},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7216644883155823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336256861686707},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5679031610488892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5512555241584778},{"id":"https://openalex.org/C35304006","wikidata":"https://www.wikidata.org/wiki/Q5962","display_name":"Boltzmann constant","level":2,"score":0.5037023425102234},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.4854913055896759},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48000210523605347},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4697437882423401},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4666692316532135},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4335760176181793},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42512083053588867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4210435748100281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35441386699676514},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10653609037399292},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1162/neco_a_00311","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00311","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:22509963","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22509963","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.7709","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.7709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/%7Ersalakhu/www/papers/MIT-CSAIL-TR-2010-037.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.258.7198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.258.7198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://learning.cs.toronto.edu/%7Ehinton/absps/efficientDBM.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.259.1292","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.259.1292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.utstat.toronto.edu/%7Ersalakhu/papers/neco_DBM.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/57474","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/57474","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/57474","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/57474","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W66838807","https://openalex.org/W142185896","https://openalex.org/W145818128","https://openalex.org/W177847060","https://openalex.org/W189596042","https://openalex.org/W193851967","https://openalex.org/W205159212","https://openalex.org/W645920547","https://openalex.org/W1513873506","https://openalex.org/W1516111018","https://openalex.org/W1526741802","https://openalex.org/W1543614656","https://openalex.org/W1578739277","https://openalex.org/W1665214252","https://openalex.org/W1746680969","https://openalex.org/W1813659000","https://openalex.org/W1981276685","https://openalex.org/W1990838964","https://openalex.org/W1993882792","https://openalex.org/W1994616650","https://openalex.org/W1997865285","https://openalex.org/W1999817190","https://openalex.org/W2020999234","https://openalex.org/W2024060531","https://openalex.org/W2025768430","https://openalex.org/W2029949252","https://openalex.org/W2037048515","https://openalex.org/W2043285245","https://openalex.org/W2064487597","https://openalex.org/W2072128103","https://openalex.org/W2081801065","https://openalex.org/W2083380015","https://openalex.org/W2084336274","https://openalex.org/W2096192494","https://openalex.org/W2099866409","https://openalex.org/W2099939455","https://openalex.org/W2100002341","https://openalex.org/W2100495367","https://openalex.org/W2100618437","https://openalex.org/W2102409316","https://openalex.org/W2103359087","https://openalex.org/W2110361616","https://openalex.org/W2110798204","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2124914669","https://openalex.org/W2129363682","https://openalex.org/W2132172482","https://openalex.org/W2134557905","https://openalex.org/W2134653808","https://openalex.org/W2135884179","https://openalex.org/W2136922672","https://openalex.org/W2139427956","https://openalex.org/W2142773971","https://openalex.org/W2144935315","https://openalex.org/W2149845449","https://openalex.org/W2150529939","https://openalex.org/W2157002241","https://openalex.org/W2157629899","https://openalex.org/W2159737176","https://openalex.org/W2246822104","https://openalex.org/W2346626577","https://openalex.org/W2567948266","https://openalex.org/W2595697910","https://openalex.org/W2596585349","https://openalex.org/W2597289420","https://openalex.org/W2612972698","https://openalex.org/W2613634265","https://openalex.org/W2725061391","https://openalex.org/W2990138404","https://openalex.org/W3014462022","https://openalex.org/W4231109964","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2064630666","https://openalex.org/W3121598771","https://openalex.org/W2902142523","https://openalex.org/W2287713958","https://openalex.org/W3010338767","https://openalex.org/W2193475944","https://openalex.org/W2119341610","https://openalex.org/W2028660548","https://openalex.org/W3124769812","https://openalex.org/W2402196265"],"abstract_inverted_index":{"We":[0,113,139],"present":[1,114],"a":[2,21,29,88,109,151],"new":[3],"learning":[4,80],"algorithm":[5],"for":[6,48],"Boltzmann":[7,69,126,148],"machines":[8,70,127,149],"that":[9,24,55,92,124,142],"contain":[10],"many":[11],"layers":[12,74,159],"of":[13,43,53,60,77,133,160],"hidden":[14,73,158],"variables.":[15],"Data-dependent":[16],"statistics":[17,34],"are":[18,35,150,165],"estimated":[19,36],"using":[20,37,87],"variational":[22,102],"approximation":[23],"tends":[25],"to":[26,67,104,155],"focus":[27],"on":[28,116],"single":[30,110],"mode,":[31],"and":[32,75,119,136],"data-independent":[33],"persistent":[38],"Markov":[39],"chains.":[40],"The":[41,79,97],"use":[42],"two":[44,51],"quite":[45],"different":[46],"techniques":[47],"estimating":[49],"the":[50,58,61,94,101,117,143,157],"types":[52],"statistic":[54],"enter":[56],"into":[57],"gradient":[59],"log":[62],"likelihood":[63],"makes":[64],"it":[65],"practical":[66],"learn":[68,128],"with":[71,108],"multiple":[72],"millions":[76],"parameters.":[78],"can":[81],"be":[82,105],"made":[83],"more":[84],"efficient":[85],"by":[86,146],"layer-by-layer":[89],"pretraining":[90,98],"phase":[91],"initializes":[93],"weights":[95],"sensibly.":[96],"also":[99,140],"allows":[100],"inference":[103],"initialized":[106],"sensibly":[107],"bottom-up":[111],"pass.":[112],"results":[115],"MNIST":[118],"NORB":[120],"data":[121],"sets":[122],"showing":[123],"deep":[125,147],"very":[129,152],"good":[130],"generative":[131],"models":[132],"handwritten":[134],"digits":[135],"3D":[137],"objects.":[138],"show":[141],"features":[144],"discovered":[145],"effective":[153],"way":[154],"initialize":[156],"feedforward":[161],"neural":[162],"nets,":[163],"which":[164],"then":[166],"discriminatively":[167],"fine-tuned.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":46},{"year":2021,"cited_by_count":47},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":59},{"year":2018,"cited_by_count":59},{"year":2017,"cited_by_count":40},{"year":2016,"cited_by_count":56},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":26},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}