{"id":"https://openalex.org/W2982534372","doi":"https://doi.org/10.1109/tnnls.2021.3086757","title":"Multivariate Uncertainty in Deep Learning","display_name":"Multivariate Uncertainty in Deep Learning","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W2982534372","doi":"https://doi.org/10.1109/tnnls.2021.3086757","mag":"2982534372","pmid":"https://pubmed.ncbi.nlm.nih.gov/34138723"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3086757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3086757","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.14215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065521265","display_name":"Rebecca L. Russell","orcid":"https://orcid.org/0000-0002-4012-4513"},"institutions":[{"id":"https://openalex.org/I1343143571","display_name":"Draper Laboratory","ror":"https://ror.org/04378d909","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343143571"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebecca L. Russell","raw_affiliation_strings":["The Charles Stark Draper Laboratory, Inc., Cambridge, MA, USA","[The Charles Stark Draper Laboratory, Inc., Cambridge, MA 02139 USA (e-mail: rrussell@draper.com)]"],"raw_orcid":"https://orcid.org/0000-0002-4012-4513","affiliations":[{"raw_affiliation_string":"The Charles Stark Draper Laboratory, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I1343143571"]},{"raw_affiliation_string":"[The Charles Stark Draper Laboratory, Inc., Cambridge, MA 02139 USA (e-mail: rrussell@draper.com)]","institution_ids":["https://openalex.org/I1343143571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022670728","display_name":"Christopher Reale","orcid":"https://orcid.org/0000-0002-3978-9577"},"institutions":[{"id":"https://openalex.org/I1343143571","display_name":"Draper Laboratory","ror":"https://ror.org/04378d909","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343143571"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Reale","raw_affiliation_strings":["The Charles Stark Draper Laboratory, Inc., Cambridge, MA, USA","The Charles Stark Draper Laboratory, Inc., Cambridge, MA 02139, USA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-3978-9577","affiliations":[{"raw_affiliation_string":"The Charles Stark Draper Laboratory, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I1343143571"]},{"raw_affiliation_string":"The Charles Stark Draper Laboratory, Inc., Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I1343143571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1343143571"],"apc_list":null,"apc_paid":null,"fwci":1.0992,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81200622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"12","first_page":"7937","last_page":"7943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","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"}},"topics":[{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9926999807357788,"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":0.6894955039024353},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.6053327322006226},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.5987581014633179},{"id":"https://openalex.org/keywords/ensemble-kalman-filter","display_name":"Ensemble Kalman filter","score":0.5823127031326294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5795135498046875},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.5790468454360962},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5657390356063843},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.527525007724762},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.44004249572753906},{"id":"https://openalex.org/keywords/estimation-of-covariance-matrices","display_name":"Estimation of covariance matrices","score":0.4375791549682617},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42299219965934753},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41370338201522827},{"id":"https://openalex.org/keywords/extended-kalman-filter","display_name":"Extended Kalman filter","score":0.369423508644104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25227534770965576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23971644043922424},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.21401959657669067},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18061912059783936}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894955039024353},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.6053327322006226},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.5987581014633179},{"id":"https://openalex.org/C79334102","wikidata":"https://www.wikidata.org/wiki/Q3072268","display_name":"Ensemble Kalman filter","level":4,"score":0.5823127031326294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5795135498046875},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5790468454360962},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5657390356063843},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.527525007724762},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.44004249572753906},{"id":"https://openalex.org/C180877172","wikidata":"https://www.wikidata.org/wiki/Q5401390","display_name":"Estimation of covariance matrices","level":3,"score":0.4375791549682617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42299219965934753},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41370338201522827},{"id":"https://openalex.org/C206833254","wikidata":"https://www.wikidata.org/wiki/Q5421817","display_name":"Extended Kalman filter","level":3,"score":0.369423508644104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25227534770965576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23971644043922424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.21401959657669067},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18061912059783936}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tnnls.2021.3086757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3086757","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34138723","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34138723","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":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:1910.14215","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14215","pdf_url":"https://arxiv.org/pdf/1910.14215","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:2982534372","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.14215.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.1910.14215","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.14215","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.14215","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14215","pdf_url":"https://arxiv.org/pdf/1910.14215","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":[{"id":"https://openalex.org/G3240770402","display_name":null,"funder_award_id":"HR0011-16-S-0001","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982534372.pdf","grobid_xml":"https://content.openalex.org/works/W2982534372.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W2074232022","https://openalex.org/W2084002884","https://openalex.org/W2105934661","https://openalex.org/W2113325037","https://openalex.org/W2133352538","https://openalex.org/W2143541671","https://openalex.org/W2145498142","https://openalex.org/W2149764047","https://openalex.org/W2150066425","https://openalex.org/W2156064084","https://openalex.org/W2169901455","https://openalex.org/W2194775991","https://openalex.org/W2200124539","https://openalex.org/W2212012417","https://openalex.org/W2555820268","https://openalex.org/W2563015642","https://openalex.org/W2598706937","https://openalex.org/W2600383743","https://openalex.org/W2613718673","https://openalex.org/W2890955732","https://openalex.org/W2896860804","https://openalex.org/W2899771611","https://openalex.org/W2949867636","https://openalex.org/W2951266961","https://openalex.org/W2963203809","https://openalex.org/W2963238274","https://openalex.org/W2963371290","https://openalex.org/W2963714390","https://openalex.org/W2964059111","https://openalex.org/W3101088080","https://openalex.org/W6617145748","https://openalex.org/W6620707391","https://openalex.org/W6681709612","https://openalex.org/W6712730493","https://openalex.org/W6730042731","https://openalex.org/W6730099391","https://openalex.org/W6735443497","https://openalex.org/W6764214684","https://openalex.org/W6768581196"],"related_works":["https://openalex.org/W3207450959","https://openalex.org/W3049165116","https://openalex.org/W2904979775","https://openalex.org/W2799977193","https://openalex.org/W2891998654","https://openalex.org/W188036482","https://openalex.org/W3206865772","https://openalex.org/W3010129597","https://openalex.org/W3189050980","https://openalex.org/W3104672407","https://openalex.org/W3107734508","https://openalex.org/W2563954902","https://openalex.org/W2965875443","https://openalex.org/W3083397657","https://openalex.org/W2963729465","https://openalex.org/W3199064820","https://openalex.org/W3200439229","https://openalex.org/W3038915618","https://openalex.org/W2999046867","https://openalex.org/W3120421313"],"abstract_inverted_index":{"Deep":[0],"learning":[1,51,74],"has":[2],"the":[3,69,143,154],"potential":[4,71],"to":[5,15,36,75,88,182],"dramatically":[6,58],"impact":[7,145],"navigation":[8],"and":[9,18,29,59,80,101,126,161],"tracking":[10,141],"state":[11,23],"estimation":[12,24],"problems":[13,94],"critical":[14],"autonomous":[16],"vehicles":[17],"robotics.":[19],"Measurement":[20],"uncertainties":[21],"in":[22,53,82,115,138,168],"systems":[25],"based":[26],"on":[27,153],"Kalman":[28,133,155],"other":[30],"Bayes":[31],"filters":[32],"are":[33],"typically":[34],"assumed":[35],"be":[37,76],"a":[38,109,120,132,139,169],"fixed":[39],"covariance":[40,112],"matrix.":[41],"This":[42],"assumption":[43],"is":[44],"risky,":[45],"particularly":[46],"for":[47,68,92,158,184],"\"black":[48],"box\"":[49],"deep":[50,73,110],"models,":[52],"which":[54],"uncertainty":[55,65,91,111,149,180],"can":[56,151,178],"vary":[57],"unexpectedly.":[60],"Accurate":[61],"quantification":[62,150],"of":[63,72,104],"multivariate":[64,90,121,148],"will":[66],"allow":[67,179],"full":[70],"used":[77],"more":[78],"safely":[79],"reliably":[81],"these":[83],"applications.":[84],"We":[85,107,135,165],"show":[86,137],"how":[87,174],"model":[89,114],"regression":[93],"with":[95],"neural":[96],"networks,":[97],"incorporating":[98],"both":[99,159],"aleatoric":[100],"epistemic":[102],"sources":[103],"heteroscedastic":[105],"uncertainty.":[106],"train":[108],"matrix":[113],"two":[116],"ways:":[117],"directly":[118],"using":[119,128],"Gaussian":[122],"density":[123],"loss":[124],"function":[125],"indirectly":[127],"end-to-end":[129,175],"training":[130,177],"through":[131],"filter.":[134],"experimentally":[136],"visual":[140,171],"problem":[142],"large":[144],"that":[146],"accurate":[147],"have":[152],"filter":[156,176,185],"performance":[157],"in-domain":[160],"out-of-domain":[162],"evaluation":[163],"data.":[164],"additionally":[166],"show,":[167],"challenging":[170],"odometry":[172],"problem,":[173],"predictions":[181],"compensate":[183],"weaknesses.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}