{"id":"https://openalex.org/W2319974058","doi":null,"title":"Similarity-based Contrastive Divergence Methods for Energy-based Deep Learning Models","display_name":"Similarity-based Contrastive Divergence Methods for Energy-based Deep Learning Models","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2319974058","mag":"2319974058"},"language":"en","primary_location":{"id":"pmh:oai:raiith.iith.ac.in:5513","doi":null,"is_oa":true,"landing_page_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","pdf_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103476017","display_name":"Adepu Ravi Sankar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Adepu Ravi Sankar","raw_affiliation_strings":["Indian Institute of Technology Hyderabad, Sang\u0101reddi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad, Sang\u0101reddi, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038020125","display_name":"Vineeth Nallure Balasubramanian","orcid":"https://orcid.org/0000-0003-2656-0375","observed_orcids":["https://orcid.org/0000-0003-2656-0375"]},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineeth N Balasubramanian","raw_affiliation_strings":["Indian Institute of Technology Indore, Indore, India"],"raw_orcid":"https://orcid.org/0000-0003-2656-0375","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Indore, Indore, India","institution_ids":["https://openalex.org/I64295750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3586,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48305015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7465999722480774,"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":0.7465999722480774,"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":0.0560000017285347,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.03799999877810478,"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/contrastive-divergence","display_name":"contrastive divergence","score":0.8970000147819519},{"id":"https://openalex.org/keywords/energy-based-models","display_name":"energy-based models","score":0.7300000190734863},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"restricted Boltzmann machine","score":0.9179999828338623},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.7889999747276306},{"id":"https://openalex.org/keywords/markov-chain-mixing","display_name":"Markov chain mixing","score":0.8629999756813049},{"id":"https://openalex.org/keywords/log-likelihood-approximation","display_name":"log-likelihood approximation","score":0.5920000076293945},{"id":"https://openalex.org/keywords/deep-learning-training","display_name":"deep learning training","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8262069225311279},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.716219961643219},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.6652200818061829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6089522242546082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918844938278198},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.5506925582885742},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.539302408695221},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.515096127986908},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.514106810092926},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4780993163585663},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4246673583984375},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41678181290626526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41353267431259155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36774158477783203},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3020942211151123},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:raiith.iith.ac.in:5513","doi":null,"is_oa":true,"landing_page_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","pdf_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"mag:2319974058","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v45/Sankar15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417739","display_name":"Asian Conference on Machine Learning","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":"Asian Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:raiith.iith.ac.in:5513","doi":null,"is_oa":true,"landing_page_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","pdf_url":"http://raiith.iith.ac.in/5513/1/JMLR_2015%20ACML.pdf","source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2319974058.pdf","grobid_xml":"https://content.openalex.org/works/W2319974058.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W142185896","https://openalex.org/W1495672967","https://openalex.org/W1596986901","https://openalex.org/W2018168021","https://openalex.org/W2116064496","https://openalex.org/W2116825644","https://openalex.org/W2130325614","https://openalex.org/W2136163184","https://openalex.org/W2136922672","https://openalex.org/W2145287260","https://openalex.org/W2150529939","https://openalex.org/W2163605009","https://openalex.org/W2181347294"],"related_works":["https://openalex.org/W7015266658","https://openalex.org/W4383469139","https://openalex.org/W2996607545","https://openalex.org/W3213145015","https://openalex.org/W4221143297","https://openalex.org/W2964042503","https://openalex.org/W2782603171","https://openalex.org/W4389471179","https://openalex.org/W2274369480","https://openalex.org/W3009318622"],"abstract_inverted_index":{"Energy-based":[0],"deep":[1,130],"learning":[2,131,161],"models":[3,17],"like":[4],"Restricted":[5],"Boltzmann":[6],"Machines":[7],"are":[8],"increasingly":[9],"used":[10,118],"for":[11,26],"real-world":[12],"applications.":[13],"However,":[14],"all":[15,120,128],"these":[16],"inherently":[18],"depend":[19],"on":[20,135,139],"the":[21,35,103,111,150,171],"Contrastive":[22],"Divergence":[23],"(CD)":[24],"method":[25,115],"training":[27],"and":[28,62,74,126,146,162],"maximization":[29],"of":[30,33,59,67,122,152,158,167,170],"log":[31,168],"likelihood":[32,169],"generating":[34],"given":[36],"data":[37,100],"distribution.":[38],"CD,":[39],"which":[40,97],"internally":[41],"uses":[42,98],"Gibbs":[43],"sampling,":[44],"often":[45],"does":[46],"not":[47],"perform":[48],"well":[49],"due":[50],"to":[51,80,92,101,106],"issues":[52],"such":[53,69],"as":[54,70],"biased":[55],"samples,":[56],"poor":[57],"mixing":[58],"Markov":[60,104],"chains":[61],"highmass":[63],"probability":[64,112],"modes.":[65],"Variants":[66],"CD":[68,123],"PCD,":[71],"Fast":[72],"PCD":[73],"Tempered":[75],"MCMC":[76],"have":[77],"been":[78],"proposed":[79],"address":[81],"this":[82,85,137,153],"issue.":[83],"In":[84],"work,":[86],"we":[87],"propose":[88],"a":[89,164],"new":[90,108],"approach":[91,138],"CDbased":[93],"methods,":[94],"called":[95],"Diss-CD,":[96],"dissimilar":[99],"allow":[102],"chain":[105],"explore":[107],"modes":[109],"in":[110,160],"space.":[113],"This":[114],"can":[116],"be":[117],"with":[119],"variants":[121],"(or":[124],"PCD),":[125],"across":[127],"energy-based":[129],"models.":[132],"Our":[133],"experiments":[134],"using":[136],"standard":[140],"datasets":[141],"including":[142],"MNIST,":[143],"Caltech-101":[144],"Silhouette":[145],"Synthetic":[147],"Transformations,":[148],"demonstrate":[149],"promise":[151],"approach,":[154],"showing":[155],"fast":[156],"convergence":[157],"error":[159],"also":[163],"better":[165],"approximation":[166],"data.":[172]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}