{"id":"https://openalex.org/W2243290847","doi":"https://doi.org/10.1109/icassp.2016.7472159","title":"Batch normalized recurrent neural networks","display_name":"Batch normalized recurrent neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2243290847","doi":"https://doi.org/10.1109/icassp.2016.7472159","mag":"2243290847"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1510.01378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104037191","display_name":"C\u00e9sar Laurent","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":true,"raw_author_name":"Cesar Laurent","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","Universit\u00e8 de Montreal"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098880","display_name":"Gabriel Pereyra","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Pereyra","raw_affiliation_strings":["University of Southern California","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047130674","display_name":"Phil\u00e9mon Brakel","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":"Philemon Brakel","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","Universit\u00e8 de Montreal"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"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":"Ying Zhang","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al","Universit\u00e8 de Montreal"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["CIFAR Fellow","University of Southern California","Universit\u00e8 de Montreal"],"affiliations":[{"raw_affiliation_string":"CIFAR Fellow","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104037191"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":3.9756,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94190448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2657","last_page":"2661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/normalization","display_name":"Normalization (sociology)","score":0.9156855344772339},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8242659568786621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477598786354065},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.7082933783531189},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6173878312110901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563156247138977},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.552265465259552},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.52684086561203},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.43424808979034424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4322896897792816},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42140254378318787},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41901448369026184},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4142734408378601},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1513669490814209},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10206380486488342},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.1010502278804779}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9156855344772339},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8242659568786621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477598786354065},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.7082933783531189},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6173878312110901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563156247138977},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.552265465259552},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.52684086561203},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.43424808979034424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4322896897792816},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42140254378318787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41901448369026184},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4142734408378601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1513669490814209},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10206380486488342},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.1010502278804779},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2016.7472159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1510.01378","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1510.01378","pdf_url":"https://arxiv.org/pdf/1510.01378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2243290847","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1510.01378.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1510.01378","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1510.01378","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1510.01378","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1510.01378","pdf_url":"https://arxiv.org/pdf/1510.01378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2243290847.pdf","grobid_xml":"https://content.openalex.org/works/W2243290847.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1591801644","https://openalex.org/W1606347560","https://openalex.org/W1889624880","https://openalex.org/W1915968771","https://openalex.org/W1917432393","https://openalex.org/W2005708641","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2113021982","https://openalex.org/W2117539524","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2949117887","https://openalex.org/W2949190276","https://openalex.org/W2951793508","https://openalex.org/W2964308564","https://openalex.org/W4285719527","https://openalex.org/W6631943919","https://openalex.org/W6635446068","https://openalex.org/W6636649193","https://openalex.org/W6638545294","https://openalex.org/W6638667902","https://openalex.org/W6639497327","https://openalex.org/W6640002369","https://openalex.org/W6640090968","https://openalex.org/W6674330103","https://openalex.org/W6679434410","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W2949117887","https://openalex.org/W2326533993","https://openalex.org/W2064675550","https://openalex.org/W3006673621","https://openalex.org/W3061525482","https://openalex.org/W2942604505","https://openalex.org/W2252143850","https://openalex.org/W2787911558","https://openalex.org/W2963685250","https://openalex.org/W2512629640","https://openalex.org/W2751220357","https://openalex.org/W2807087769","https://openalex.org/W2945313542","https://openalex.org/W2786043755","https://openalex.org/W2963454111","https://openalex.org/W3092616613","https://openalex.org/W2996170846","https://openalex.org/W2029897006","https://openalex.org/W3201561669","https://openalex.org/W3128955336"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Networks":[2],"(RNNs)":[3],"are":[4,20],"powerful":[5],"models":[6],"for":[7,83],"sequential":[8],"data":[9],"that":[10,33,92],"have":[11],"the":[12,93,105,113],"potential":[13],"to":[14,23,27,58,63,79,100,111],"learn":[15],"long-term":[16],"dependencies.":[17],"However,":[18],"they":[19],"computationally":[21],"expensive":[22],"train":[24],"and":[25,89],"difficult":[26],"parallelize.":[28],"Recent":[29],"work":[30],"has":[31],"shown":[32,62],"normalizing":[34],"intermediate":[35],"representations":[36],"of":[37,104],"neural":[38,47],"networks":[39,48],"can":[40,76],"significantly":[41,64],"improve":[42,112],"convergence":[43,103],"rates":[44],"in":[45],"feed-forward":[46],"[1].":[49],"In":[50,68],"particular,":[51],"batch":[52,74,97],"normalization,":[53],"which":[54],"uses":[55],"mini-batch":[56],"statistics":[57],"standardize":[59],"features,":[60],"was":[61],"reduce":[65],"training":[66,106],"time.":[67],"this":[69],"paper,":[70],"we":[71,95],"investigate":[72],"how":[73],"normalization":[75,98],"be":[77],"applied":[78],"RNNs.":[80],"We":[81],"show":[82],"both":[84],"a":[85,101],"speech":[86],"recognition":[87],"task":[88],"language":[90],"modeling":[91],"way":[94],"apply":[96],"leads":[99],"faster":[102],"criterion":[107],"but":[108],"doesn't":[109],"seem":[110],"generalization":[114],"performance.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}