{"id":"https://openalex.org/W66838807","doi":null,"title":"On Contrastive Divergence Learning.","display_name":"On Contrastive Divergence Learning.","publication_year":2005,"publication_date":"2005-01-06","ids":{"openalex":"https://openalex.org/W66838807","mag":"66838807"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.219","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/aistats/fullpapers/217.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5057957982","display_name":"Miguel \u00c1. Carreira-Perpi\u00f1\u00e1n","orcid":"https://orcid.org/0000-0003-3297-9375","observed_orcids":["https://orcid.org/0000-0003-3297-9375"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miguel \u00c1. Carreira-Perpi\u00f1\u00e1n","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3297-9375","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffrey E. Hinton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3555,"has_fulltext":false,"cited_by_count":643,"citation_normalized_percentile":{"value":0.97971594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.41670000553131104,"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/T10320","display_name":"Neural Networks and Applications","score":0.41670000553131104,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.3244999945163727,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.13109999895095825,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contrastive-divergence","display_name":"contrastive divergence","score":0.8769999742507935},{"id":"https://openalex.org/keywords/markov-random-fields","display_name":"Markov random fields","score":0.9729999899864197},{"id":"https://openalex.org/keywords/maximum-likelihood-learning","display_name":"maximum likelihood training","score":0.9110000133514404},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.9010000228881836},{"id":"https://openalex.org/keywords/parameter-estimation","display_name":"parameter estimation","score":0.4180000126361847},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968058705329895},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.4952830374240875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44750863313674927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40784576535224915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3365488648414612},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07298925518989563}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.219","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/aistats/fullpapers/217.pdf","raw_type":"text"},{"id":"mag:66838807","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/r5/carreira-perpinan05a/carreira-perpinan05a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419146","display_name":"International Conference on Artificial Intelligence and Statistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Artificial Intelligence and Statistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W5796403","https://openalex.org/W190267059","https://openalex.org/W1568229137","https://openalex.org/W1651266332","https://openalex.org/W1802356529","https://openalex.org/W1813659000","https://openalex.org/W2082092506","https://openalex.org/W2095844239","https://openalex.org/W2110361616","https://openalex.org/W2116064496","https://openalex.org/W2130313186","https://openalex.org/W2130416410","https://openalex.org/W2142773971","https://openalex.org/W2157444450","https://openalex.org/W2482531687"],"related_works":["https://openalex.org/W1511867968","https://openalex.org/W7098913902","https://openalex.org/W2158570381","https://openalex.org/W7101146511","https://openalex.org/W2142773971","https://openalex.org/W7096095652","https://openalex.org/W2296501131","https://openalex.org/W2963580052","https://openalex.org/W3176559922","https://openalex.org/W102776102"],"abstract_inverted_index":{"Maximum-likelihood":[0],"(ML)":[1],"learning":[2,54,71,89,109,124],"of":[3,13,20,79,87],"Markov":[4,22,44],"random":[5,80],"fields":[6],"is":[7,46,103],"challenging":[8],"because":[9],"it":[10,60,93],"requires":[11],"estimates":[12,96],"averages":[14],"that":[15,41,92,100],"have":[16],"an":[17,118],"exponential":[18],"number":[19],"terms.":[21],"chain":[23,45],"Monte":[24],"Carlo":[25],"methods":[26],"typically":[27,104],"take":[28],"a":[29,50,63],"long":[30],"time":[31],"to":[32,76,114,117,129],"converge":[33],"on":[34],"unbiased":[35],"estimates,":[36],"but":[37,99],"Hinton":[38],"(2002)":[39],"showed":[40],"if":[42],"the":[43,53,85,101,131],"only":[47],"run":[48],"for":[49],"few":[51],"steps,":[52],"can":[55,110,125],"still":[56],"work":[57],"well":[58],"and":[59,90,121],"approximately":[61],"minimizes":[62],"di#erent":[64],"function":[65],"called":[66],"\"contrastive":[67],"divergence\"":[68],"(CD).":[69],"CD":[70,88,108,132],"has":[72],"been":[73],"successfully":[74],"applied":[75],"various":[77],"types":[78],"fields.":[81],"Here,":[82],"we":[83],"study":[84],"properties":[86],"show":[91],"provides":[94],"biased":[95],"in":[97],"general,":[98],"bias":[102],"very":[105],"small.":[106],"Fast":[107],"therefore":[111],"be":[112,127],"used":[113,128],"get":[115],"close":[116],"ML":[119,123],"solution":[120],"slow":[122],"then":[126],"fine-tune":[130],"solution.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":54},{"year":2019,"cited_by_count":50},{"year":2018,"cited_by_count":61},{"year":2017,"cited_by_count":62},{"year":2016,"cited_by_count":54},{"year":2015,"cited_by_count":46},{"year":2014,"cited_by_count":53},{"year":2013,"cited_by_count":37},{"year":2012,"cited_by_count":24}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}