{"id":"https://openalex.org/W4205915266","doi":"https://doi.org/10.1109/bigdata52589.2021.9671328","title":"Assessing Deep Neural Networks as Probability Estimators","display_name":"Assessing Deep Neural Networks as Probability Estimators","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205915266","doi":"https://doi.org/10.1109/bigdata52589.2021.9671328"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671328","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","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/A5101459185","display_name":"Yu Pan","orcid":"https://orcid.org/0000-0001-7515-8492"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Pan","raw_affiliation_strings":["University of Nebraska-Lincoln, Lincoln, NE, USA"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024434501","display_name":"Kwo\u2010Sen Kuo","orcid":"https://orcid.org/0000-0001-7644-4140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwo-Sen Kuo","raw_affiliation_strings":["Bayesics, LLC, Bowie, MD, USA"],"affiliations":[{"raw_affiliation_string":"Bayesics, LLC, Bowie, MD, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046476658","display_name":"M. L. Rilee","orcid":"https://orcid.org/0000-0002-5478-7190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael L. Rilee","raw_affiliation_strings":["Bayesics, LLC, Bowie, MD, USA"],"affiliations":[{"raw_affiliation_string":"Bayesics, LLC, Bowie, MD, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020745360","display_name":"Hongfeng Yu","orcid":"https://orcid.org/0000-0002-0596-8227"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfeng Yu","raw_affiliation_strings":["University of Nebraska-Lincoln, Lincoln, NE, USA"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101459185"],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":null,"apc_paid":null,"fwci":0.0653,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37053571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1083","last_page":"1091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9979000091552734,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9937000274658203,"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/T10320","display_name":"Neural Networks and Applications","score":0.9884999990463257,"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/estimator","display_name":"Estimator","score":0.6900503635406494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6561715006828308},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5996469855308533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5080327987670898},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4755553603172302},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3302212059497833},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24639257788658142},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16768679022789001}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6900503635406494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561715006828308},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5996469855308533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080327987670898},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4755553603172302},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3302212059497833},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24639257788658142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16768679022789001}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671328","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1579853615","https://openalex.org/W1719489212","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1964168965","https://openalex.org/W2026915078","https://openalex.org/W2048971218","https://openalex.org/W2111854888","https://openalex.org/W2114858870","https://openalex.org/W2125389028","https://openalex.org/W2187089797","https://openalex.org/W2556372419","https://openalex.org/W2626967530","https://openalex.org/W2739748921","https://openalex.org/W2804078698","https://openalex.org/W2952716587","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963684088","https://openalex.org/W2964024144","https://openalex.org/W2964080999","https://openalex.org/W3016484931","https://openalex.org/W4229658977","https://openalex.org/W4297663084","https://openalex.org/W4298289240","https://openalex.org/W6637568146","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6718362372","https://openalex.org/W6729966448","https://openalex.org/W6730269975","https://openalex.org/W6730746255","https://openalex.org/W6739651123","https://openalex.org/W6741832134","https://openalex.org/W6752378368","https://openalex.org/W6755312952","https://openalex.org/W6776358511"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4,162],"performed":[5],"admirably":[6],"in":[7,105],"classification":[8,15,59,171],"tasks.":[9],"However,":[10],"the":[11,29,48,54,58,75,79,86,93,106,120,131,144,154,159,166],"characterization":[12],"of":[13,61,77,133,146,149],"their":[14],"uncertainties,":[16],"required":[17],"for":[18,43],"certain":[19],"applications,":[20],"has":[21],"been":[22],"lacking.":[23],"In":[24],"this":[25],"work,":[26],"we":[27,128],"investigate":[28],"issue":[30],"by":[31,85],"assessing":[32],"DNNs\u2019":[33,147,170],"ability":[34],"to":[35,66,74,112,119,169],"estimate":[36],"conditional":[37,80],"probabilities":[38,81],"and":[39,53,110,125,140,151,158],"propose":[40],"a":[41,63,67,99,116],"framework":[42],"systematic":[44],"uncertainty":[45],"characterization.":[46],"Denoting":[47],"input":[49,69],"sample":[50],"as":[51,56,83],"x":[52,70],"category":[55,64],"y,":[57],"task":[60,76],"assigning":[62],"y":[65],"given":[68],"can":[71],"be":[72],"reduced":[73],"estimating":[78],"p(y|x),":[82,150],"approximated":[84],"DNN":[87],"at":[88],"its":[89],"last":[90],"layer":[91],"using":[92],"softmax":[94,97],"function.":[95],"Since":[96],"yields":[98],"vector":[100],"whose":[101],"elements":[102],"all":[103],"fall":[104],"interval":[107],"(0,":[108],"1)":[109],"sum":[111],"1,":[113],"it":[114],"suggests":[115],"probabilistic":[117],"interpretation":[118],"DNN\u2019s":[121],"outcome.":[122],"Using":[123],"synthetic":[124],"real-world":[126],"datasets,":[127],"look":[129],"into":[130],"impact":[132],"various":[134],"factors,":[135],"e.g.,":[136],"probability":[137,156,168],"density":[138,157],"f(x)":[139],"inter-categorical":[141,160],"sparsity,":[142],"on":[143],"precision":[145],"estimations":[148],"find":[152],"that":[153],"likelihood":[155],"sparsity":[161],"greater":[163],"impacts":[164],"than":[165],"prior":[167],"uncertainty.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}