{"id":"https://openalex.org/W2626194254","doi":"https://doi.org/10.1162/neco_a_01174","title":"Gated Orthogonal Recurrent Units: On Learning to Forget","display_name":"Gated Orthogonal Recurrent Units: On Learning to Forget","publication_year":2019,"publication_date":"2019-02-15","ids":{"openalex":"https://openalex.org/W2626194254","doi":"https://doi.org/10.1162/neco_a_01174","mag":"2626194254","pmid":"https://pubmed.ncbi.nlm.nih.gov/30764742"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01174","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01174","pdf_url":"https://direct.mit.edu/neco/article-pdf/31/4/765/1050504/neco_a_01174.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/neco/article-pdf/31/4/765/1050504/neco_a_01174.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100386741","display_name":"Li Jing","orcid":"https://orcid.org/0000-0001-8675-2390"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Li Jing","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041145688","display_name":"\u00c7a\u01e7lar G\u00fcl\u00e7ehre","orcid":"https://orcid.org/0009-0003-4124-1687"},"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":"Caglar Gulcehre","raw_affiliation_strings":["University of Montreal, Montreal H3T, 1J4, Quebec, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Montreal H3T, 1J4, Quebec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003041665","display_name":"John Peurifoy","orcid":"https://orcid.org/0000-0003-2423-8091"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Peurifoy","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103227508","display_name":"Yichen Shen","orcid":"https://orcid.org/0000-0002-7512-3756"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yichen Shen","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091601455","display_name":"Max Tegmark","orcid":"https://orcid.org/0000-0001-7670-7190"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Max Tegmark","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060426875","display_name":"Marin Solja\u010di\u0107","orcid":"https://orcid.org/0000-0002-7184-5831"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marin Soljacic","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A","institution_ids":["https://openalex.org/I63966007"]}]},{"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/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, Montreal H3T 1J4, Quebec, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Montreal H3T 1J4, Quebec, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5003041665","https://openalex.org/A5041145688","https://openalex.org/A5060426875","https://openalex.org/A5086198262","https://openalex.org/A5091601455","https://openalex.org/A5100386741","https://openalex.org/A5103227508"],"corresponding_institution_ids":["https://openalex.org/I63966007","https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":10.549,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98531745,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"31","issue":"4","first_page":"765","last_page":"783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9957000017166138,"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":0.9947999715805054,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.5317736268043518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45695048570632935},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.39482080936431885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3736497163772583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3308963179588318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33008748292922974},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3253122568130493}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317736268043518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45695048570632935},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39482080936431885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3736497163772583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3308963179588318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33008748292922974},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3253122568130493}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008128","descriptor_name":"Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008128","descriptor_name":"Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008128","descriptor_name":"Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008568","descriptor_name":"Memory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008568","descriptor_name":"Memory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008568","descriptor_name":"Memory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01174","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01174","pdf_url":"https://direct.mit.edu/neco/article-pdf/31/4/765/1050504/neco_a_01174.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:30764742","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30764742","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":{"id":"doi:10.1162/neco_a_01174","is_oa":true,"landing_page_url":"https://doi.org/10.1162/neco_a_01174","pdf_url":"https://direct.mit.edu/neco/article-pdf/31/4/765/1050504/neco_a_01174.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2423344179","display_name":null,"funder_award_id":"CCF-1640012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3229309168","display_name":"E2CDA: Type I: Collaborative Research: Energy Efficient Computing with Chip-Based Photonics","funder_award_id":"1640012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4198030508","display_name":null,"funder_award_id":"2016-EP-2693-B","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G6274897657","display_name":null,"funder_award_id":"W911NF-13","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6959854382","display_name":null,"funder_award_id":"W911NF-13-D0001","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8727049869","display_name":null,"funder_award_id":"W911NF-13","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2626194254.pdf","grobid_xml":"https://content.openalex.org/works/W2626194254.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W194249466","https://openalex.org/W1485981043","https://openalex.org/W1522301498","https://openalex.org/W1525961042","https://openalex.org/W1632114991","https://openalex.org/W1635512741","https://openalex.org/W1800356822","https://openalex.org/W1815076433","https://openalex.org/W1855892484","https://openalex.org/W1951216520","https://openalex.org/W2053831280","https://openalex.org/W2064675550","https://openalex.org/W2107878631","https://openalex.org/W2136848157","https://openalex.org/W2157331557","https://openalex.org/W2493026224","https://openalex.org/W2559655401","https://openalex.org/W2581719241","https://openalex.org/W2914584698","https://openalex.org/W2950527759","https://openalex.org/W2950898568","https://openalex.org/W2951605425","https://openalex.org/W2952507584","https://openalex.org/W2963042606","https://openalex.org/W2963992014","https://openalex.org/W2964199361","https://openalex.org/W4205167092","https://openalex.org/W4303633609"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"We":[0,34,84,106],"present":[1],"a":[2,44,54],"novel":[3],"recurrent":[4,50,71],"neural":[5],"network":[6],"(RNN)-based":[7],"model":[8,62,116],"that":[9,87,134],"combines":[10],"the":[11,19,94],"remembering":[12],"ability":[13,20,95,99],"of":[14,21,114],"unitary":[15,75,91],"evolution":[16,41],"RNNs":[17,23,42,52,78,92],"with":[18,43,53,111],"gated":[22,49,70],"to":[24,48,65,96],"effectively":[25],"forget":[26],"redundant":[27],"or":[28,76],"irrelevant":[29],"information":[30],"in":[31,104],"its":[32],"memory.":[33],"achieve":[35],"this":[36],"by":[37],"extending":[38],"restricted":[39],"orthogonal":[40,77,89],"gating":[45],"mechanism":[46],"similar":[47],"unit":[51],"reset":[55],"gate":[56],"and":[57,73,90,131,142],"an":[58,101,112],"update":[59],"gate.":[60],"Our":[61],"is":[63],"able":[64],"outperform":[66],"long":[67],"short-term":[68],"memory,":[69],"units,":[72],"vanilla":[74],"on":[79,117],"several":[80],"long-term-dependency":[81],"benchmark":[82],"tasks.":[83,144],"empirically":[85],"show":[86],"both":[88],"lack":[93],"forget.":[97],"This":[98],"plays":[100],"important":[102],"role":[103],"RNNs.":[105],"provide":[107],"competitive":[108],"results":[109],"along":[110],"analysis":[113],"our":[115],"many":[118],"natural":[119],"sequential":[120],"tasks,":[121],"including":[122],"question":[123],"answering,":[124],"speech":[125],"spectrum":[126],"prediction,":[127],"character-level":[128],"language":[129],"modeling,":[130],"synthetic":[132],"tasks":[133],"involve":[135],"long-term":[136],"dependencies":[137],"such":[138],"as":[139],"algorithmic,":[140],"denoising,":[141],"copying":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}