{"id":"https://openalex.org/W2105153012","doi":"https://doi.org/10.1109/icassp.2012.6288836","title":"Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines","display_name":"Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2105153012","doi":"https://doi.org/10.1109/icassp.2012.6288836","mag":"2105153012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062688417","display_name":"Christian Plahl","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Plahl","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informatik 6-Computer Science Department, RWTH Aachen University, Aachen, Germany","Lehrstuhl f\u00fcr Informatik 6, Computer Science Department, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik 6-Computer Science Department, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik 6, Computer Science Department, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Nahamoo","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4165","last_page":"4168"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T12676","display_name":"Machine Learning and ELM","score":0.9923999905586243,"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":0.9768999814987183,"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/deep-belief-network","display_name":"Deep belief network","score":0.8353201746940613},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8265882730484009},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7764163613319397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697092294692993},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.7403804659843445},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.7373006343841553},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6346749067306519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6268668174743652},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48366841673851013},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48289036750793457},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4719468951225281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4486694931983948},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4389193058013916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4164675176143646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33789557218551636},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.31982219219207764}],"concepts":[{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.8353201746940613},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8265882730484009},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7764163613319397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697092294692993},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.7403804659843445},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7373006343841553},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6346749067306519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6268668174743652},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48366841673851013},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48289036750793457},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4719468951225281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4486694931983948},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4389193058013916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4164675176143646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33789557218551636},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31982219219207764},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6288836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.1431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.1431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:127779","is_oa":false,"landing_page_url":"http://publications.rwth-aachen.de/record/127779","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012) : Kyoto, Japan, 25 - 30 March 2012 ; [proceedings] / [sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society]<br/>2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, 2012-03-25 - 2012-03-30","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2076794394","https://openalex.org/W2108335221","https://openalex.org/W2108665656","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2141778357","https://openalex.org/W2155117693","https://openalex.org/W2394932179","https://openalex.org/W6676231525","https://openalex.org/W6681419218"],"related_works":["https://openalex.org/W2064630666","https://openalex.org/W3121598771","https://openalex.org/W2287713958","https://openalex.org/W2513801676","https://openalex.org/W2916681395","https://openalex.org/W3010338767","https://openalex.org/W1257380361","https://openalex.org/W3005559199","https://openalex.org/W2133034788","https://openalex.org/W2105153012"],"abstract_inverted_index":{"Restricted":[0],"Boltzmann":[1],"Machines":[2],"(RBM)":[3],"continue":[4],"to":[5,10,34,38,43,81,92,102,111,175],"be":[6,24,82,87],"a":[7,44,68,117,142,169],"popular":[8],"methodology":[9],"pre-train":[11,103],"weights":[12],"of":[13,123,132],"Deep":[14],"Belief":[15],"Networks":[16],"(DBNs).":[17],"However,":[18],"the":[19,40,48,72,78,94,108,121,130],"RBM":[20,136],"objective":[21,79],"function":[22,33,80],"cannot":[23],"maximized":[25],"directly.":[26],"Therefore,":[27],"it":[28],"is":[29],"not":[30],"clear":[31],"what":[32],"monitor":[35],"when":[36],"deciding":[37],"stop":[39,93],"training,":[41],"leading":[42],"challenge":[45],"in":[46],"managing":[47],"computational":[49],"costs.":[50],"The":[51],"Sparse":[52],"Encoding":[53],"Symmetric":[54],"Machine":[55],"(SESM)":[56],"has":[57],"been":[58],"suggested":[59],"as":[60,89],"an":[61,90],"alternative":[62],"method":[63],"for":[64],"pre-training.":[65],"By":[66],"placing":[67],"sparseness":[69],"term":[70],"on":[71,139],"NN":[73],"output":[74],"codebook,":[75],"SESM":[76,101,124,133,155,167],"allows":[77],"optimized":[83],"directly":[84],"and":[85,105,125,135,141,156,161],"reliably":[86],"monitored":[88],"indicator":[91],"training.":[95],"In":[96],"this":[97,107],"paper,":[98],"we":[99,115,128],"explore":[100],"DBNs":[104,138,153,165],"apply":[106],"first":[109],"time":[110],"speech":[112],"recognition.":[113],"First,":[114],"provide":[116],"detailed":[118],"analysis":[119],"comparing":[120],"behavior":[122],"RBM.":[126,176],"Second,":[127],"compare":[129],"performance":[131,160],"pre-trained":[134,137,152],"TIMIT":[140],"50":[143],"hour":[144],"English":[145],"Broadcast":[146],"News":[147],"task.":[148],"Results":[149],"indicate":[150],"that":[151],"using":[154],"RBMs":[157],"achieve":[158],"comparable":[159],"outperform":[162],"randomly":[163],"initialized":[164],"with":[166],"providing":[168],"much":[170],"easier":[171],"stopping":[172],"criterion":[173],"relative":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}