{"id":"https://openalex.org/W2136848157","doi":"https://doi.org/10.1162/089976600300015015","title":"Learning to Forget: Continual Prediction with LSTM","display_name":"Learning to Forget: Continual Prediction with LSTM","publication_year":2000,"publication_date":"2000-10-01","ids":{"openalex":"https://openalex.org/W2136848157","doi":"https://doi.org/10.1162/089976600300015015","mag":"2136848157","pmid":"https://pubmed.ncbi.nlm.nih.gov/11032042"},"language":"en","primary_location":{"id":"doi:10.1162/089976600300015015","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976600300015015","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044994184","display_name":"Felix A. Gers","orcid":"https://orcid.org/0000-0002-2258-2983"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Felix A. Gers","raw_affiliation_strings":["IDSIA, 6900 Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDSIA, 6900 Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Schmidhuber","raw_affiliation_strings":["IDSIA, 6900 Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDSIA, 6900 Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030511075","display_name":"Fred Cummins","orcid":"https://orcid.org/0000-0003-4722-723X"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fred Cummins","raw_affiliation_strings":["IDSIA, 6900 Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDSIA, 6900 Lugano, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044994184"],"corresponding_institution_ids":["https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":10.7671,"has_fulltext":false,"cited_by_count":5317,"citation_normalized_percentile":{"value":0.98230109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"10","first_page":"2451","last_page":"2471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T10320","display_name":"Neural Networks and Applications","score":0.998199999332428,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8521074056625366},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.7573972940444946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505472302436829},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7323083281517029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6308976411819458},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5377258658409119},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5230090022087097},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.450858473777771},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4484371244907379},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31028831005096436}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8521074056625366},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.7573972940444946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505472302436829},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7323083281517029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6308976411819458},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5377258658409119},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5230090022087097},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.450858473777771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4484371244907379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31028831005096436},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008570","descriptor_name":"Memory, Short-Term","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008570","descriptor_name":"Memory, Short-Term","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},{"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":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1162/089976600300015015","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976600300015015","pdf_url":null,"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:11032042","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11032042","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W152658472","https://openalex.org/W1522426752","https://openalex.org/W1674799117","https://openalex.org/W1963605035","https://openalex.org/W1971129545","https://openalex.org/W1982291194","https://openalex.org/W1997449813","https://openalex.org/W2057653135","https://openalex.org/W2064675550","https://openalex.org/W2086756055","https://openalex.org/W2103452139","https://openalex.org/W2107878631","https://openalex.org/W2114471683","https://openalex.org/W2121029939","https://openalex.org/W2121553911","https://openalex.org/W2129831132","https://openalex.org/W2137269967","https://openalex.org/W2154890045","https://openalex.org/W2731782018","https://openalex.org/W3133056632","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W96259911","https://openalex.org/W4385608460","https://openalex.org/W2168225754","https://openalex.org/W2370772865","https://openalex.org/W2000034628","https://openalex.org/W1528611913","https://openalex.org/W2387487224","https://openalex.org/W4366146733"],"abstract_inverted_index":{"Long":[0],"short-term":[1],"memory":[2],"(LSTM;":[3],"Hochreiter":[4],"&":[5],"Schmidhuber,":[6],"1997)":[7],"can":[8],"solve":[9,114],"numerous":[10],"tasks":[11],"not":[12,36],"solvable":[13],"by":[14],"previous":[15],"learning":[16],"algorithms":[17,109],"for":[18],"recurrent":[19],"neural":[20],"networks":[21,29],"(RNNs).":[22],"We":[23,95],"identify":[24],"a":[25,37,73],"weakness":[26],"of":[27,117],"LSTM":[28,81,103,120],"processing":[30],"continual":[31,115],"input":[32],"streams":[33],"that":[34,78],"are":[35],"priori":[38],"segmented":[39],"into":[40],"subsequences":[41],"with":[42,121],"explicitly":[43],"marked":[44],"ends":[45],"at":[46,88],"which":[47,101],"the":[48,57,65],"network's":[49],"internal":[50,93],"state":[51,58],"could":[52],"be":[53],"reset.":[54],"Without":[55],"resets,":[56],"may":[59],"grow":[60],"indefinitely":[61],"and":[62,128],"eventually":[63],"cause":[64],"network":[66],"to":[67,83,85,113],"break":[68],"down.":[69],"Our":[70],"remedy":[71],"is":[72],"novel,":[74],"adaptive":[75],"\"forget":[76],"gate\"":[77],"enables":[79],"an":[80,130],"cell":[82],"learn":[84],"reset":[86],"itself":[87],"appropriate":[89],"times,":[90],"thus":[91],"releasing":[92],"resources.":[94],"review":[96],"illustrative":[97],"benchmark":[98],"problems":[99],"on":[100],"standard":[102],"outperforms":[104],"other":[105],"RNN":[106],"algorithms.":[107],"All":[108],"(including":[110],"LSTM)":[111],"fail":[112],"versions":[116],"these":[118],"problems.":[119],"forget":[122],"gates,":[123],"however,":[124],"easily":[125],"solves":[126],"them,":[127],"in":[129],"elegant":[131],"way.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":132},{"year":2025,"cited_by_count":650},{"year":2024,"cited_by_count":640},{"year":2023,"cited_by_count":667},{"year":2022,"cited_by_count":621},{"year":2021,"cited_by_count":632},{"year":2020,"cited_by_count":559},{"year":2019,"cited_by_count":510},{"year":2018,"cited_by_count":370},{"year":2017,"cited_by_count":233},{"year":2016,"cited_by_count":125},{"year":2015,"cited_by_count":47},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}