{"id":"https://openalex.org/W2930029601","doi":"https://doi.org/10.1109/tnnls.2020.2980004","title":"Correlated Parameters to Accurately Measure Uncertainty in Deep Neural Networks","display_name":"Correlated Parameters to Accurately Measure Uncertainty in Deep Neural Networks","publication_year":2020,"publication_date":"2020-04-17","ids":{"openalex":"https://openalex.org/W2930029601","doi":"https://doi.org/10.1109/tnnls.2020.2980004","mag":"2930029601","pmid":"https://pubmed.ncbi.nlm.nih.gov/32310784"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2980004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2980004","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/9365681/09070148.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/5962385/9365681/09070148.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043972469","display_name":"Konstantin Posch","orcid":"https://orcid.org/0000-0002-3602-638X"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Konstantin Posch","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria","Department of Statistics , University of Klagenfurt , Klagenfurt, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3602-638X","affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"Department of Statistics , University of Klagenfurt , Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086682451","display_name":"J\u00fcrgen Pilz","orcid":"https://orcid.org/0000-0001-9365-4916"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Juergen Pilz","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria","Department of Statistics , University of Klagenfurt , Klagenfurt, Austria"],"raw_orcid":"https://orcid.org/0000-0001-9365-4916","affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"Department of Statistics , University of Klagenfurt , Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210166741"],"apc_list":null,"apc_paid":null,"fwci":0.4063,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67907226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"32","issue":"3","first_page":"1037","last_page":"1051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9995999932289124,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9995999932289124,"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":0.9973999857902527,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9952999949455261,"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":0.7518652677536011},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6514416933059692},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5874934196472168},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5494894981384277},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5164852142333984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5029794573783875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500852108001709},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.47209352254867554},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46991056203842163},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45849525928497314},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4389580488204956},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.43318235874176025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4262383282184601},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39459389448165894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35176563262939453},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16267716884613037},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14551594853401184}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7518652677536011},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6514416933059692},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5874934196472168},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5494894981384277},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5164852142333984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5029794573783875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500852108001709},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.47209352254867554},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46991056203842163},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45849525928497314},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4389580488204956},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.43318235874176025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4262383282184601},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39459389448165894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35176563262939453},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16267716884613037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14551594853401184},{"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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tnnls.2020.2980004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2980004","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/9365681/09070148.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:32310784","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32310784","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:1904.01334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.01334","pdf_url":"https://arxiv.org/pdf/1904.01334","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":null,"raw_type":"text"},{"id":"mag:2930029601","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.01334","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.1904.01334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.01334","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":"article"}],"best_oa_location":{"id":"doi:10.1109/tnnls.2020.2980004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2980004","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/9365681/09070148.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2773297097","display_name":null,"funder_award_id":"783163","funder_id":"https://openalex.org/F4320327207","funder_display_name":"Electronic Components and Systems for European Leadership"},{"id":"https://openalex.org/G3729258792","display_name":"Integrated Development 4.0","funder_award_id":"783163","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320327207","display_name":"Electronic Components and Systems for European Leadership","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2930029601.pdf","grobid_xml":"https://content.openalex.org/works/W2930029601.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W100623710","https://openalex.org/W601603264","https://openalex.org/W1006163277","https://openalex.org/W1506806321","https://openalex.org/W1520168181","https://openalex.org/W1567512734","https://openalex.org/W1686810756","https://openalex.org/W1826234144","https://openalex.org/W1963704256","https://openalex.org/W1965555277","https://openalex.org/W2007339694","https://openalex.org/W2027197837","https://openalex.org/W2033178790","https://openalex.org/W2047229728","https://openalex.org/W2073241381","https://openalex.org/W2095705004","https://openalex.org/W2108677974","https://openalex.org/W2112796928","https://openalex.org/W2127538960","https://openalex.org/W2139701068","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2164411961","https://openalex.org/W2182396527","https://openalex.org/W2194775991","https://openalex.org/W2273369333","https://openalex.org/W2302053044","https://openalex.org/W2345010043","https://openalex.org/W2557738935","https://openalex.org/W2586702902","https://openalex.org/W2605055943","https://openalex.org/W2675203311","https://openalex.org/W2727300753","https://openalex.org/W2741366276","https://openalex.org/W2762409611","https://openalex.org/W2766110843","https://openalex.org/W2772084711","https://openalex.org/W2807414627","https://openalex.org/W2922145560","https://openalex.org/W2951548721","https://openalex.org/W2962973320","https://openalex.org/W2964059111","https://openalex.org/W2972188071","https://openalex.org/W3118608800","https://openalex.org/W4244577065","https://openalex.org/W6600213771","https://openalex.org/W6617145748","https://openalex.org/W6618476874","https://openalex.org/W6637373629","https://openalex.org/W6638836233","https://openalex.org/W6674330103","https://openalex.org/W6676315081","https://openalex.org/W6679143118","https://openalex.org/W6684191040","https://openalex.org/W6697490744","https://openalex.org/W6730042731","https://openalex.org/W6735443497","https://openalex.org/W6736244717","https://openalex.org/W6740512805","https://openalex.org/W6741844306","https://openalex.org/W6760208186","https://openalex.org/W6764214684","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2959490256","https://openalex.org/W3009733954","https://openalex.org/W2953263857","https://openalex.org/W2808648791","https://openalex.org/W2950467202","https://openalex.org/W3000041653","https://openalex.org/W2970325798","https://openalex.org/W3168162192","https://openalex.org/W1912123407","https://openalex.org/W1507470542","https://openalex.org/W2951983780","https://openalex.org/W1968994649","https://openalex.org/W2418082485","https://openalex.org/W2989991760","https://openalex.org/W2949177905","https://openalex.org/W2612661529","https://openalex.org/W66306528","https://openalex.org/W2950952738","https://openalex.org/W2577761826","https://openalex.org/W2327051950"],"abstract_inverted_index":{"In":[0,62],"this":[1],"article,":[2],"a":[3,101,123],"novel":[4],"approach":[5,50,140,190],"for":[6,20],"training":[7],"deep":[8],"neural":[9],"networks":[10],"using":[11],"Bayesian":[12,17,149],"techniques":[13],"is":[14,29,67,141],"presented.":[15],"The":[16,48,99,135],"methodology":[18],"allows":[19],"an":[21],"easy":[22],"evaluation":[23],"of":[24,72,137,152,180],"model":[25],"uncertainty":[26,184,195],"and,":[27],"additionally,":[28],"robust":[30],"to":[31,45,56,87,91,95,118,128],"overfitting.":[32],"These":[33],"are":[34,104,116,156],"commonly":[35],"the":[36,58,64,70,88,92,108,114,138,153,157,166,169,173,181,188,198],"two":[37],"main":[38],"problems":[39],"classical,":[40],"i.e.,":[41],"non-Bayesian":[42,133],"architectures":[43],"have":[44],"struggle":[46],"with.":[47],"proposed":[49,170],"applies":[51],"variational":[52,65],"inference":[53],"in":[54],"order":[55],"approximate":[57],"intractable":[59],"posterior":[60],"distribution.":[61],"particular,":[63],"distribution":[66,84],"defined":[68,105],"as":[69],"product":[71],"multiple":[73],"multivariate":[74],"normal":[75,83],"distributions":[76],"with":[77,132,145],"tridiagonal":[78],"covariance":[79],"matrices.":[80],"Every":[81],"single":[82],"belongs":[85],"either":[86],"weights":[89],"or":[90],"biases":[93],"corresponding":[94,109],"one":[96,171],"network":[97],"layer.":[98],"layerwise":[100],"posteriori":[102],"variances":[103],"based":[106],"on":[107],"expectation":[110],"values,":[111],"and":[112,143,163],"furthermore,":[113],"correlations":[115],"assumed":[117],"be":[119,129],"identical.":[120],"Therefore,":[121],"only":[122],"few":[124],"additional":[125],"parameters":[126],"need":[127],"optimized":[130],"compared":[131,144],"settings.":[134],"performance":[136,154],"new":[139,189],"evaluated":[142],"other":[146],"recently":[147],"developed":[148],"methods.":[150,200],"Basis":[151],"evaluations":[155,179],"popular":[158],"benchmark":[159],"data":[160],"sets":[161],"MNIST":[162],"CIFAR-10.":[164],"Among":[165],"considered":[167],"approaches,":[168],"shows":[172],"best":[174],"predictive":[175],"accuracy.":[176],"Moreover,":[177],"extensive":[178],"provided":[182],"prediction":[183],"information":[185],"indicate":[186],"that":[187],"often":[191],"yields":[192],"more":[193],"useful":[194],"estimates":[196],"than":[197],"comparison":[199]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}