{"id":"https://openalex.org/W2150529939","doi":"https://doi.org/10.1145/1553374.1553506","title":"Using fast weights to improve persistent contrastive divergence","display_name":"Using fast weights to improve persistent contrastive divergence","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2150529939","doi":"https://doi.org/10.1145/1553374.1553506","mag":"2150529939"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553506","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5013146947","display_name":"Tijmen Tieleman","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":true,"raw_author_name":"Tijmen Tieleman","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, 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":["University of Toronto, Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013146947"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":18.043,"has_fulltext":false,"cited_by_count":279,"citation_normalized_percentile":{"value":0.99443385,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1033","last_page":"1040"},"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":0.9994000196456909,"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":0.9994000196456909,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9987999796867371,"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":0.9980000257492065,"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/markov-chain","display_name":"Markov chain","score":0.7432256937026978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6467517614364624},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.498856782913208},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4810519516468048},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48013922572135925},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.47128668427467346},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.43261295557022095},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.3367413878440857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26173579692840576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17641347646713257},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08118775486946106}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7432256937026978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467517614364624},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.498856782913208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4810519516468048},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48013922572135925},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.47128668427467346},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.43261295557022095},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3367413878440857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26173579692840576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17641347646713257},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08118775486946106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1553374.1553506","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4520","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/363.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.8882","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.8882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.duke.edu/~lcarin/FastGibbsMixing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1594106604","https://openalex.org/W1813659000","https://openalex.org/W1964155876","https://openalex.org/W1994616650","https://openalex.org/W2069514727","https://openalex.org/W2083380015","https://openalex.org/W2089614885","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2134557905","https://openalex.org/W2136922672","https://openalex.org/W2567948266","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2151689585","https://openalex.org/W2380816257","https://openalex.org/W3087071515","https://openalex.org/W4283726152","https://openalex.org/W3093571331","https://openalex.org/W1981914504","https://openalex.org/W1485888979","https://openalex.org/W1546022168","https://openalex.org/W2806680938","https://openalex.org/W4302285290"],"abstract_inverted_index":{"The":[0,159],"most":[1],"commonly":[2],"used":[3],"learning":[4,50],"algorithm":[5],"for":[6,26],"restricted":[7],"Boltzmann":[8],"machines":[9],"is":[10,104],"contrastive":[11],"divergence":[12],"which":[13],"starts":[14],"a":[15,19,28,33,60,152],"Markov":[16,116,126],"chain":[17,25,127,141],"at":[18],"data":[20,72],"point":[21],"and":[22,114,131,168],"runs":[23],"the":[24,39,43,56,83,87,95,108,111,115,121,125,156,173,179],"only":[27],"few":[29],"iterations":[30],"to":[31,71,92,106,128,150,172],"get":[32],"cheap,":[34],"low":[35],"variance":[36],"estimate":[37],"of":[38,63,147],"sufficient":[40],"statistics":[41,58],"under":[42],"model.":[44,180],"Tieleman":[45],"(2008)":[46],"showed":[47],"that":[48,67,120,142,177],"better":[49],"can":[51],"be":[52],"achieved":[53],"by":[54],"estimating":[55],"model's":[57],"using":[59,132],"small":[61,80],"set":[62,146],"persistent":[64],"\"fantasy":[65],"particles\"":[66],"are":[68],"not":[69,170],"reinitialized":[70],"points":[73],"after":[74],"each":[75],"weight":[76,81,101,112,122],"update.":[77],"With":[78],"sufficiently":[79],"updates,":[82],"fantasy":[84],"particles":[85],"represent":[86],"equilibrium":[88],"distribution":[89],"accurately":[90],"but":[91,164],"explain":[93],"why":[94],"method":[96],"works":[97],"with":[98],"much":[99],"larger":[100],"updates":[102,113,123],"it":[103],"necessary":[105],"consider":[107],"interaction":[109],"between":[110],"chain.":[117],"We":[118],"show":[119],"force":[124],"mix":[129],"fast,":[130],"this":[133],"insight":[134],"we":[135],"develop":[136],"an":[137,144],"even":[138],"faster":[139],"mixing":[140],"uses":[143],"auxiliary":[145],"\"fast":[148],"weights\"":[149],"implement":[151],"temporary":[153],"overlay":[154],"on":[155],"energy":[157,175],"landscape.":[158],"fast":[160],"weights":[161],"learn":[162],"rapidly":[163,167],"also":[165],"decay":[166],"do":[169],"contribute":[171],"normal":[174],"landscape":[176],"defines":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":27},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":22}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}