{"id":"https://openalex.org/W3146135289","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534258","title":"Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation","display_name":"Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3146135289","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534258","mag":"3146135289"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.15682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041199105","display_name":"Mathias L\u00f6we","orcid":"https://orcid.org/0000-0003-1954-9653"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Mathias Lowe","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","IT-UNIVERSITY OF COPENHAGEN"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"IT-UNIVERSITY OF COPENHAGEN","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102393799","display_name":"Per Lunnemann Hansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Per Lunnemann","raw_affiliation_strings":["Blackwood Seven, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Blackwood Seven, Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020511097","display_name":"Sebastian Risi","orcid":"https://orcid.org/0000-0003-3607-8400"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sebastian Risi","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","IT-UNIVERSITY OF COPENHAGEN"],"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"IT-UNIVERSITY OF COPENHAGEN","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041199105"],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04162442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9966999888420105,"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":0.9926999807357788,"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/interpretability","display_name":"Interpretability","score":0.8258246779441833},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6625093221664429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5817029476165771},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.539627730846405},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5193094611167908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5188168883323669},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5060541033744812},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4961112439632416},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4626525342464447},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45448705554008484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4017203450202942},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3908524513244629},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3623632490634918},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30455026030540466},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20495706796646118}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8258246779441833},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6625093221664429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817029476165771},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.539627730846405},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5193094611167908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5188168883323669},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5060541033744812},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4961112439632416},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4626525342464447},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45448705554008484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017203450202942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3908524513244629},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3623632490634918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30455026030540466},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20495706796646118}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.15682","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.15682","pdf_url":"https://arxiv.org/pdf/2103.15682","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:3146135289","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.15682.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.2103.15682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.15682","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.15682","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.15682","pdf_url":"https://arxiv.org/pdf/2103.15682","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3784521206","display_name":null,"funder_award_id":"8053-00073B","funder_id":"https://openalex.org/F4320313796","funder_display_name":"Innovationsfonden"}],"funders":[{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W92982764","https://openalex.org/W639708223","https://openalex.org/W1567512734","https://openalex.org/W1571206560","https://openalex.org/W1582774210","https://openalex.org/W1663973292","https://openalex.org/W1959608418","https://openalex.org/W1988115241","https://openalex.org/W2038606746","https://openalex.org/W2045656233","https://openalex.org/W2065450924","https://openalex.org/W2108677974","https://openalex.org/W2149298154","https://openalex.org/W2162602080","https://openalex.org/W2217402295","https://openalex.org/W2225156818","https://openalex.org/W2267236547","https://openalex.org/W2302202015","https://openalex.org/W2557283755","https://openalex.org/W2592505114","https://openalex.org/W2763323349","https://openalex.org/W2810438149","https://openalex.org/W2896556344","https://openalex.org/W2911546748","https://openalex.org/W2938553652","https://openalex.org/W2941708750","https://openalex.org/W2947000318","https://openalex.org/W2950177356","https://openalex.org/W2963090522","https://openalex.org/W2963552443","https://openalex.org/W2963977107","https://openalex.org/W2974922583","https://openalex.org/W2979693376","https://openalex.org/W3003921671","https://openalex.org/W3006861283","https://openalex.org/W3030163527","https://openalex.org/W3037939899","https://openalex.org/W3101806332","https://openalex.org/W3123857276","https://openalex.org/W3140968660","https://openalex.org/W4232976691","https://openalex.org/W4248681815","https://openalex.org/W4255421341","https://openalex.org/W6603695008","https://openalex.org/W6610566761","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6676315081","https://openalex.org/W6679529799","https://openalex.org/W6733901433","https://openalex.org/W6744093492","https://openalex.org/W6758854563","https://openalex.org/W6768581196","https://openalex.org/W6770847983","https://openalex.org/W6778883912","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3203684173","https://openalex.org/W3126837587","https://openalex.org/W2168841621","https://openalex.org/W2922146890","https://openalex.org/W2893686399","https://openalex.org/W1877071675","https://openalex.org/W2257410811","https://openalex.org/W1969798062","https://openalex.org/W2067720358","https://openalex.org/W589111785","https://openalex.org/W3163232994","https://openalex.org/W2590286530","https://openalex.org/W2945677996","https://openalex.org/W2514135854","https://openalex.org/W2046380768","https://openalex.org/W2735957303","https://openalex.org/W3102888966","https://openalex.org/W2476591869","https://openalex.org/W3035208301","https://openalex.org/W245192467"],"abstract_inverted_index":{"We":[0,154,172],"introduce":[1],"a":[2,17,35,41,44,122,132,139,151,165],"novel":[3],"combination":[4],"of":[5,26,34,40,62,83,90,97,141,184,205],"Bayesian":[6],"Models":[7],"(BMs)":[8],"and":[9,32],"Neural":[10],"Networks":[11],"(NNs)":[12],"for":[13,106,150,187],"making":[14,46],"predictions":[15,47,158],"with":[16,37,48,87,164,176,201],"minimum":[18],"expected":[19,51],"risk.":[20],"Our":[21,101],"approach":[22,102,175],"combines":[23],"the":[24,29,38,49,56,63,81,84,88,95,104,111,129,136,145,169,182,189,206],"best":[25],"both":[27],"worlds,":[28],"data":[30,126,185,198],"efficiency":[31],"interpretability":[33],"BM":[36],"speed":[39],"NN.":[42,190,207],"For":[43,79],"BM,":[45],"lowest":[50],"loss":[52,167],"requires":[53],"integrating":[54],"over":[55],"posterior":[57,64,147],"distribution.":[58],"When":[59],"exact":[60],"inference":[61],"predictive":[65,148,203],"distribution":[66,149],"is":[67,192],"intractable,":[68],"approximation":[69],"methods":[70,163],"are":[71],"typically":[72],"applied,":[73],"e.g.":[74],"Monte":[75],"Carlo":[76],"(MC)":[77],"simulation.":[78],"MC,":[80],"variance":[82],"estimator":[85],"decreases":[86],"number":[89],"samples":[91],"\u2013":[92],"but":[93],"at":[94,113],"expense":[96],"increased":[98],"computational":[99],"cost.":[100],"removes":[103],"need":[105],"iterative":[107],"MC":[108],"simulation":[109],"on":[110,168],"CPU":[112],"prediction":[114],"time.":[115],"In":[116,131],"brief,":[117],"it":[118],"works":[119],"by":[120,194],"fitting":[121,188],"NN":[123,137],"to":[124,144,180],"synthetic":[125],"generated":[127],"using":[128],"BM.":[130],"single":[133],"feed-forward":[134],"pass,":[135],"gives":[138],"set":[140],"point-wise":[142],"approximations":[143],"BM's":[146],"given":[152],"observation.":[153],"achieve":[155],"risk":[156],"minimized":[157],"significantly":[159],"faster":[160],"than":[161],"standard":[162],"negligible":[166],"test":[170],"dataset.":[171],"combine":[173],"this":[174],"Active":[177],"Learning":[178],"(AL)":[179],"minimize":[181],"amount":[183],"required":[186],"This":[191],"done":[193],"iteratively":[195],"labeling":[196],"more":[197],"in":[199],"regions":[200],"high":[202],"uncertainty":[204]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}