{"id":"https://openalex.org/W2921915536","doi":"https://doi.org/10.1109/icassp40776.2020.9053498","title":"Indylstms: Independently Recurrent LSTMS","display_name":"Indylstms: Independently Recurrent LSTMS","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2921915536","doi":"https://doi.org/10.1109/icassp40776.2020.9053498","mag":"2921915536"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.08023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043020378","display_name":"Pedro Gonnet","orcid":"https://orcid.org/0000-0003-4509-7291"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Gonnet","raw_affiliation_strings":["Google Research","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009225557","display_name":"Thomas Deselaers","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Deselaers","raw_affiliation_strings":["Google Research","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3352","last_page":"3356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9994999766349792,"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/overfitting","display_name":"Overfitting","score":0.8727421760559082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267855405807495},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7053406238555908},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6351932287216187},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5598990321159363},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.5304868817329407},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5304372310638428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045849084854126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4613087475299835},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45828503370285034},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.44665026664733887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4371994733810425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21594664454460144},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10559192299842834},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10027626156806946}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8727421760559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267855405807495},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7053406238555908},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6351932287216187},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5598990321159363},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.5304868817329407},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5304372310638428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045849084854126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4613087475299835},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45828503370285034},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.44665026664733887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4371994733810425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21594664454460144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10559192299842834},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10027626156806946},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.08023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08023","pdf_url":"https://arxiv.org/pdf/1903.08023","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:2921915536","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.08023","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.1903.08023","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.08023","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":"Preprint"},{"id":"doi:10.17023/ktn7-gm88","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ktn7-gm88","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.08023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08023","pdf_url":"https://arxiv.org/pdf/1903.08023","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921915536.pdf","grobid_xml":"https://content.openalex.org/works/W2921915536.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1485981043","https://openalex.org/W1533861849","https://openalex.org/W1978964824","https://openalex.org/W2064675550","https://openalex.org/W2109664771","https://openalex.org/W2127141656","https://openalex.org/W2152550252","https://openalex.org/W2156338447","https://openalex.org/W2157331557","https://openalex.org/W2396666837","https://openalex.org/W2553303224","https://openalex.org/W2553397501","https://openalex.org/W2565532197","https://openalex.org/W2585720638","https://openalex.org/W2626194254","https://openalex.org/W2732547613","https://openalex.org/W2768320620","https://openalex.org/W2805275761","https://openalex.org/W2895713185","https://openalex.org/W2920854715","https://openalex.org/W2963047498","https://openalex.org/W2963513932","https://openalex.org/W2964121744","https://openalex.org/W2964325005","https://openalex.org/W2964347220","https://openalex.org/W3004690717","https://openalex.org/W6616837769","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6676373471","https://openalex.org/W6721158474","https://openalex.org/W6729956949","https://openalex.org/W6731194115","https://openalex.org/W6745767635","https://openalex.org/W6751922908","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W2964035032","https://openalex.org/W3037514364","https://openalex.org/W3174401451","https://openalex.org/W2460550122","https://openalex.org/W2886490473","https://openalex.org/W2972340269","https://openalex.org/W2157140289","https://openalex.org/W3095592098","https://openalex.org/W2604700561","https://openalex.org/W2949794196","https://openalex.org/W2652900013","https://openalex.org/W3167504114","https://openalex.org/W2161591461","https://openalex.org/W2910580498","https://openalex.org/W3128513838","https://openalex.org/W2770331030","https://openalex.org/W3199418160","https://openalex.org/W3094458826","https://openalex.org/W2752514874","https://openalex.org/W8561325"],"abstract_inverted_index":{"We":[0,131,155],"introduce":[1],"Independently":[2],"Recurrent":[3],"Long":[4],"Short-term":[5],"Memory":[6],"cells:":[7],"IndyLSTMs.":[8],"These":[9],"differ":[10],"from":[11],"regular":[12,94,141],"LSTM":[13,39,95],"cells":[14,60],"in":[15,61,81,86,98,144,151],"that":[16,133],"the":[17,33,43,52,55,59,62,73,82,87,114,161],"recurrent":[18],"weights":[19],"are":[20],"not":[21],"modeled":[22],"as":[23,28,49,89,122,124],"a":[24,29],"full":[25],"matrix,":[26,31],"but":[27],"diagonal":[30],"i.e.":[32],"output":[34],"and":[35,45,54,71,102,117,150],"state":[36],"of":[37,57,66,75,84,127,146],"each":[38],"cell":[40],"depends":[41],"on":[42,113,125],"inputs":[44],"its":[46],"own":[47],"output/state,":[48],"opposed":[50,90],"to":[51,91,160,166],"input":[53],"outputs/states":[56],"all":[58],"layer.":[63],"The":[64],"number":[65,74,83],"parameters":[67],"per":[68,77,148],"Indy-LSTM":[69],"layer,":[70,88],"thus":[72],"FLOPS":[76],"evaluation,":[78],"is":[79],"linear":[80],"nodes":[85],"quadratic":[92],"for":[93],"layers,":[96],"resulting":[97],"potentially":[99],"both":[100,143],"smaller":[101,137],"faster":[103],"models.We":[104],"evaluate":[105],"their":[106,136],"performance":[107,159],"experimentally":[108],"by":[109],"training":[110],"several":[111,126],"models":[112],"popular":[115],"IAM-OnDB":[116],"CASIA":[118],"online":[119],"handwriting":[120],"datasets,":[121],"well":[123],"our":[128],"in-house":[129],"datasets.":[130],"show":[132],"IndyLSTMs,":[134],"despite":[135],"size,":[138],"consistently":[139],"outperform":[140],"LSTMs":[142],"terms":[145],"accuracy":[147,153],"parameter,":[149],"best":[152],"overall.":[154],"attribute":[156],"this":[157],"improved":[158],"IndyLSTMs":[162],"being":[163],"less":[164],"prone":[165],"overfitting.":[167]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}