{"id":"https://openalex.org/W2108563286","doi":"https://doi.org/10.1109/icassp.2013.6639349","title":"Advances in optimizing recurrent networks","display_name":"Advances in optimizing recurrent networks","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2108563286","doi":"https://doi.org/10.1109/icassp.2013.6639349","mag":"2108563286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["University of Montreal, Canada","U. Montreal, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"U. Montreal, Montreal, QC, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037330846","display_name":"Nicolas Boulanger-Lewandowski","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nicolas Boulanger-Lewandowski","raw_affiliation_strings":["University of Montreal, Canada","U. Montreal, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"U. Montreal, Montreal, QC, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043910056","display_name":"Razvan Pascanu","orcid":"https://orcid.org/0000-0002-5470-1238"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Razvan Pascanu","raw_affiliation_strings":["University of Montreal, Canada","U. Montreal, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"U. Montreal, Montreal, QC, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086198262"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":49.4235,"has_fulltext":false,"cited_by_count":483,"citation_normalized_percentile":{"value":0.9987055,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8624","last_page":"8628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9945999979972839,"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":0.9945999979972839,"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/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9861999750137329,"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/computer-science","display_name":"Computer science","score":0.7453609108924866},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6994573473930359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5207881331443787},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5035340189933777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42635518312454224},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.4263349175453186},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42278391122817993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453609108924866},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6994573473930359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5207881331443787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5035340189933777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42635518312454224},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.4263349175453186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42278391122817993},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W60493759","https://openalex.org/W194249466","https://openalex.org/W196761320","https://openalex.org/W1408639475","https://openalex.org/W1498436455","https://openalex.org/W1547547196","https://openalex.org/W1665214252","https://openalex.org/W1819710477","https://openalex.org/W1999965501","https://openalex.org/W2001263627","https://openalex.org/W2032676284","https://openalex.org/W2064675550","https://openalex.org/W2072128103","https://openalex.org/W2097998348","https://openalex.org/W2099257174","https://openalex.org/W2107878631","https://openalex.org/W2110798204","https://openalex.org/W2111304802","https://openalex.org/W2120480077","https://openalex.org/W2135181320","https://openalex.org/W2135341757","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2156387975","https://openalex.org/W2163605009","https://openalex.org/W2171928131","https://openalex.org/W2172174689","https://openalex.org/W2252143850","https://openalex.org/W2253807446","https://openalex.org/W2402302915","https://openalex.org/W2606321545","https://openalex.org/W2618530766","https://openalex.org/W2950789693","https://openalex.org/W2962968839","https://openalex.org/W2969945254","https://openalex.org/W4231109964","https://openalex.org/W4285719527","https://openalex.org/W6608133726","https://openalex.org/W6628131027","https://openalex.org/W6637242042","https://openalex.org/W6674385629","https://openalex.org/W6676481782","https://openalex.org/W6678242812","https://openalex.org/W6679825673","https://openalex.org/W6680300913","https://openalex.org/W6680498451","https://openalex.org/W6682889407","https://openalex.org/W6684191040","https://openalex.org/W6684753728"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W4380075502"],"abstract_inverted_index":{"After":[0],"a":[1],"more":[2,38,114],"than":[3],"decade-long":[4],"period":[5],"of":[6,14,41,74,84,91,100,145],"relatively":[7],"little":[8],"research":[9],"activity":[10],"in":[11,31,34,65,69,72,148],"the":[12,53,85,89,98,142],"area":[13],"recurrent":[15,42,60],"neural":[16],"networks,":[17],"several":[18],"new":[19],"developments":[20],"will":[21],"be":[22],"reviewed":[23],"here":[24,96],"that":[25],"have":[26,46],"allowed":[27],"substantial":[28],"progress":[29],"both":[30,151],"understanding":[32],"and":[33,50,119,127,136,139,153],"technical":[35],"solutions":[36],"towards":[37],"efficient":[39],"training":[40,78,152],"networks.":[43],"These":[44],"advances":[45],"been":[47],"motivated":[48],"by":[49,81],"related":[51],"to":[52,123],"optimization":[54],"issues":[55],"surrounding":[56],"deep":[57],"learning.":[58],"Although":[59],"networks":[61],"are":[62,132],"extremely":[63],"powerful":[64,115],"what":[66],"they":[67],"can":[68],"principle":[70],"represent":[71],"terms":[73],"modeling":[75],"sequences,":[76],"their":[77],"is":[79],"plagued":[80],"two":[82],"aspects":[83],"same":[86],"issue":[87],"regarding":[88],"learning":[90],"long-term":[92],"dependencies.":[93],"Experiments":[94],"reported":[95],"evaluate":[97],"use":[99],"clipping":[101],"gradients,":[102],"spanning":[103],"longer":[104],"time":[105],"ranges":[106],"with":[107],"leaky":[108],"integration,":[109],"advanced":[110],"momentum":[111],"techniques,":[112],"using":[113],"output":[116],"probability":[117],"models,":[118],"encouraging":[120],"sparser":[121],"gradients":[122],"help":[124],"symmetry":[125],"breaking":[126],"credit":[128],"assignment.":[129],"The":[130],"experiments":[131],"performed":[133],"on":[134],"text":[135],"music":[137],"data":[138],"show":[140],"off":[141],"combined":[143],"effects":[144],"these":[146],"techniques":[147],"generally":[149],"improving":[150],"test":[154],"error.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":66},{"year":2019,"cited_by_count":67},{"year":2018,"cited_by_count":66},{"year":2017,"cited_by_count":48},{"year":2016,"cited_by_count":41},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}