{"id":"https://openalex.org/W2734355239","doi":"https://doi.org/10.1109/ijcnn.2017.7965942","title":"Learning to reproduce stochastic time series using stochastic LSTM","display_name":"Learning to reproduce stochastic time series using stochastic LSTM","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2734355239","doi":"https://doi.org/10.1109/ijcnn.2017.7965942","mag":"2734355239"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5078064659","display_name":"Sadaf Gulshad","orcid":"https://orcid.org/0000-0003-3929-7174"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sadaf Gulshad","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049818689","display_name":"Dick Sigmund","orcid":"https://orcid.org/0000-0002-6207-5804"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dick Sigmund","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100718523","display_name":"Jong-Hwan Kim","orcid":"https://orcid.org/0000-0002-4172-4174"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Hwan Kim","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078064659"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.43938453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"859","last_page":"866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.998199999332428,"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/T10320","display_name":"Neural Networks and Applications","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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9940000176429749,"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/lissajous-curve","display_name":"Lissajous curve","score":0.8522701859474182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6635825037956238},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.629865288734436},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.5717493295669556},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5589054226875305},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5193094611167908},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5166645050048828},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5068739056587219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4980287551879883},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47707903385162354},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4644790589809418},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4479590356349945},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4345320463180542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3560739755630493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30105292797088623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2431737184524536}],"concepts":[{"id":"https://openalex.org/C207168407","wikidata":"https://www.wikidata.org/wiki/Q594135","display_name":"Lissajous curve","level":2,"score":0.8522701859474182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635825037956238},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.629865288734436},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.5717493295669556},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5589054226875305},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5193094611167908},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5166645050048828},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5068739056587219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4980287551879883},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47707903385162354},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4644790589809418},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4479590356349945},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4345320463180542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3560739755630493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30105292797088623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2431737184524536},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1524326598","https://openalex.org/W1695482901","https://openalex.org/W1884859883","https://openalex.org/W1959608418","https://openalex.org/W2025412857","https://openalex.org/W2058705881","https://openalex.org/W2108501770","https://openalex.org/W2126880773","https://openalex.org/W2136848157","https://openalex.org/W2146502635","https://openalex.org/W2148764920","https://openalex.org/W2159080219","https://openalex.org/W2318485605","https://openalex.org/W2555787075","https://openalex.org/W2557824989","https://openalex.org/W2587054663","https://openalex.org/W2962736495","https://openalex.org/W4302423442","https://openalex.org/W6675944832","https://openalex.org/W6681435938","https://openalex.org/W6733634088"],"related_works":["https://openalex.org/W4390491011","https://openalex.org/W2361687857","https://openalex.org/W2368717253","https://openalex.org/W2350823986","https://openalex.org/W2041612524","https://openalex.org/W2350327696","https://openalex.org/W1988279584","https://openalex.org/W2358128885","https://openalex.org/W4206085491","https://openalex.org/W2010848163"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs)":[3],"have":[4],"been":[5],"widely":[6],"used":[7],"for":[8,97,134],"complex":[9,19],"data":[10,21],"modeling.":[11],"However,":[12],"when":[13],"it":[14,106],"comes":[15],"to":[16,27,77,139,162,175],"long-term":[17],"time-dependent":[18],"sequential":[20],"modeling":[22],"with":[23,50],"stochasticities,":[24],"RNNs":[25],"seem":[26],"fail":[28],"because":[29],"of":[30,104],"vanishing":[31],"gradients":[32],"problem.":[33],"Hence,":[34],"in":[35,168],"this":[36],"paper,":[37],"we":[38],"propose":[39],"a":[40,66],"new":[41],"architecture,":[42],"stochastic":[43],"long":[44],"short":[45],"term":[46],"memory":[47],"(S-LSTM),":[48],"along":[49],"its":[51],"forward":[52],"and":[53,94,137,164],"backward":[54],"dynamics":[55],"equations.":[56],"S-LSTM":[57,159],"models":[58],"stochasticities":[59,167],"using":[60],"Bayesian":[61],"brain":[62],"hypothesis,":[63],"which":[64,73,127],"is":[65,85,121,147,160],"probabilistic":[67],"model":[68,146],"that":[69],"makes":[70],"predictions":[71],"against":[72],"samples":[74],"are":[75],"tested":[76],"update":[78],"the":[79,86,90,99,108,124,141,157,169],"conclusions":[80],"about":[81],"their":[82],"causes.":[83],"This":[84],"same":[87],"as":[88,110,112,129,173],"minimizing":[89],"difference":[91],"between":[92],"inference":[93],"posterior":[95],"densities":[96],"suppressing":[98],"free":[100],"energy.":[101],"During":[102],"training":[103],"S-LSTM,":[105],"predicts":[107],"mean":[109],"well":[111],"variance":[113,126],"at":[114],"each":[115],"time":[116],"step.":[117],"The":[118],"prediction":[119,135],"error":[120,136],"minimized":[122],"by":[123],"predicted":[125],"acts":[128],"an":[130],"inverse":[131],"weighting":[132],"factor":[133],"tries":[138],"optimize":[140],"maximum":[142],"likelihood.":[143],"Our":[144],"proposed":[145],"evaluated":[148],"through":[149],"numerical":[150],"experiments":[151],"on":[152],"noisy":[153,170],"Lissajous":[154,171],"curves.":[155],"In":[156],"experiments,":[158],"found":[161],"predict":[163],"preserve":[165],"more":[166],"curves":[172],"compared":[174],"LSTM.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}