{"id":"https://openalex.org/W7097786786","doi":null,"title":"Enhanced Gradient and Adaptive Learning Rate forTraining RestrictedBoltzmannMachines","display_name":"Enhanced Gradient and Adaptive Learning Rate forTraining RestrictedBoltzmannMachines","publication_year":2012,"publication_date":"2012-06-12","ids":{"openalex":"https://openalex.org/W7097786786"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.9496","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.9496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icml-2011.org/papers/98_icmlpaper.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5091175785","display_name":"Kyunghyun Cho","orcid":"https://orcid.org/0000-0003-1669-3211","observed_orcids":["https://orcid.org/0000-0003-1669-3211"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008894339","display_name":"Tapani Raiko","orcid":"https://orcid.org/0000-0002-0321-304X","observed_orcids":["https://orcid.org/0000-0002-0321-304X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tapani Raiko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Alexander Ilin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Ilin","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54367513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9506999850273132,"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":0.9506999850273132,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.035100001841783524,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.00139999995008111,"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/restricted-boltzmann-machine","display_name":"restricted Boltzmann machine","score":0.9079999923706055},{"id":"https://openalex.org/keywords/gradient-enhancement","display_name":"gradient enhancement","score":0.5789999961853027},{"id":"https://openalex.org/keywords/adaptive-learning-rate","display_name":"adaptive learning rate","score":0.9810000061988831},{"id":"https://openalex.org/keywords/learning-rate-schedules","display_name":"learning rate scheduling","score":0.9559999704360962},{"id":"https://openalex.org/keywords/weight-initialization","display_name":"weight initialization","score":0.8019999861717224},{"id":"https://openalex.org/keywords/greedy-learning","display_name":"greedy learning","score":0.41999998688697815},{"id":"https://openalex.org/keywords/deep-neural-network-training","display_name":"deep neural network training","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6037999987602234},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5212000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33500000834465027},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.2621999979019165},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.231.9496","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.9496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icml-2011.org/papers/98_icmlpaper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2132023809","https://openalex.org/W7096961648","https://openalex.org/W7100633568","https://openalex.org/W7095147207","https://openalex.org/W7100347142","https://openalex.org/W2727285040","https://openalex.org/W3154014598","https://openalex.org/W2593761100","https://openalex.org/W2601260342","https://openalex.org/W2529425452"],"abstract_inverted_index":{"Boltzmann":[0,23],"machines":[1],"are":[2,67],"often":[3,33],"used":[4],"as":[5,21],"building":[6],"blocks":[7],"in":[8],"greedy":[9],"learning":[10,31,42,65],"of":[11,40,76],"deep":[12],"networks.":[13],"However,":[14],"training":[15,78],"even":[16],"a":[17],"simplified":[18],"model,":[19],"known":[20],"restricted":[22],"machine":[24],"(RBM),":[25],"can":[26,55],"be":[27,56],"extremely":[28],"laborious:":[29],"Traditional":[30],"algorithms":[32,81],"converge":[34],"only":[35],"with":[36],"the":[37,41],"right":[38],"choice":[39],"rate":[43],"scheduling":[44],"and":[45],"thescaleoftheinitialweights.":[46],"Theyarealsosensitive":[47],"to":[48,70],"specific":[49],"data":[50],"representation:":[51],"An":[52],"equivalent":[53],"RBM":[54],"obtained":[57],"by":[58],"flipping":[59],"some":[60],"bits":[61],"andchangingtheweightsandbiasesaccordingly,":[62],"but":[63],"traditional":[64,80],"rules":[66],"not":[68],"invariant":[69],"such":[71],"transformations.":[72],"Without":[73],"careful":[74],"tuning":[75],"these":[77],"settings,":[79]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}