{"id":"https://openalex.org/W7081697980","doi":null,"title":"Uncertainty Estimation in Deep Neural Networks: A Comparative Study of Bayesian Approximation and Conformal Prediction","display_name":"Uncertainty Estimation in Deep Neural Networks: A Comparative Study of Bayesian Approximation and Conformal Prediction","alternate_titles":[],"publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7081697980"},"language":"en","primary_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9192215","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9192215","pdf_url":"http://lup.lub.lu.se/student-papers/record/9192215/file/9192219.pdf","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H1"},"parent_works":[],"lineage":["https://openalex.org/W7081697980"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://lup.lub.lu.se/student-papers/record/9192215/file/9192219.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122048294","display_name":"Sanne Ruijs","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijs, Sanne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122066528","display_name":"Alina Kosiakova","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kosiakova, Alina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8711000084877014,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8711000084877014,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08150000125169754,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.01140000019222498,"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/uncertainty-estimation","display_name":"uncertainty estimation","score":0.925000011920929},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.8289999961853027},{"id":"https://openalex.org/keywords/bayesian-approximation","display_name":"Bayesian approximation","score":0.7739999890327454},{"id":"https://openalex.org/keywords/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.9409999847412109},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.9779999852180481},{"id":"https://openalex.org/keywords/prediction-sets","display_name":"prediction sets","score":0.5519999861717224},{"id":"https://openalex.org/keywords/model-calibration","display_name":"model calibration","score":0.6980000138282776},{"id":"https://openalex.org/keywords/overconfidence","display_name":"overconfidence","score":0.921999990940094},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9160000085830688},{"id":"https://openalex.org/keywords/vgg16","display_name":"VGG16","score":0.9779999852180481},{"id":"https://openalex.org/keywords/googlenet","display_name":"GoogLeNet","score":0.9819999933242798},{"id":"https://openalex.org/keywords/fashion-mnist","display_name":"Fashion-MNIST","score":0.8970000147819519},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.9010000228881836}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922999978065491},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5584999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5577999949455261},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C176147448","wikidata":"https://www.wikidata.org/wiki/Q1889114","display_name":"Sensitivity analysis","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.2858999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25290000438690186},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:lup-student-papers.lub.lu.se:9192215","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9192215","pdf_url":"http://lup.lub.lu.se/student-papers/record/9192215/file/9192219.pdf","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H1"}],"best_oa_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9192215","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9192215","pdf_url":"http://lup.lub.lu.se/student-papers/record/9192215/file/9192219.pdf","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H1"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7081697980.pdf","grobid_xml":"https://content.openalex.org/works/W7081697980.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1521746852","https://openalex.org/W1553101044","https://openalex.org/W1932198206","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2254249950","https://openalex.org/W2597787948","https://openalex.org/W2626967530","https://openalex.org/W2750384547","https://openalex.org/W2886155082","https://openalex.org/W2892166671","https://openalex.org/W2909392985","https://openalex.org/W2913629080","https://openalex.org/W3025031475","https://openalex.org/W3043426275","https://openalex.org/W3102100346","https://openalex.org/W3140854437","https://openalex.org/W3147600416","https://openalex.org/W3175934715","https://openalex.org/W3183048323","https://openalex.org/W3191284406","https://openalex.org/W3196522557","https://openalex.org/W4225510469","https://openalex.org/W4281645081","https://openalex.org/W4281976359","https://openalex.org/W4289515874","https://openalex.org/W4295102975","https://openalex.org/W4361012985","https://openalex.org/W4380490520","https://openalex.org/W4382763297","https://openalex.org/W4385342469","https://openalex.org/W4387125759","https://openalex.org/W4387870527","https://openalex.org/W4388937734","https://openalex.org/W4392963937","https://openalex.org/W4399448198","https://openalex.org/W4400580373","https://openalex.org/W4401113986","https://openalex.org/W4405468052","https://openalex.org/W4410548472","https://openalex.org/W6885046811"],"related_works":["https://openalex.org/W7118704098","https://openalex.org/W7053114429","https://openalex.org/W6980662860","https://openalex.org/W2992140536","https://openalex.org/W3048139405","https://openalex.org/W3080262470","https://openalex.org/W3034666242","https://openalex.org/W3015044613","https://openalex.org/W7133184685","https://openalex.org/W4313428146"],"abstract_inverted_index":{"Deep":[0],"neural":[1,79],"networks":[2],"have":[3],"been":[4],"increasingly":[5],"used":[6],"in":[7,111,140],"various":[8],"scientific":[9],"fields":[10],"due":[11],"to":[12,34,54,73,105,146,155,170],"their":[13],"versatility":[14],"and":[15,63,84],"high":[16,20],"performance.":[17],"Despite":[18],"achieving":[19],"classification":[21,90],"accuracy,":[22],"deep":[23],"learning":[24],"models":[25],"can":[26,124],"be":[27,106],"poorly":[28],"calibrated,":[29],"assigning":[30],"overly":[31],"confident":[32],"probabilities":[33],"incorrect":[35],"predictions.":[36],"This":[37],"overconfidence":[38],"highlights":[39],"the":[40,64,88,168],"absence":[41],"of":[42,167],"built-in":[43],"mechanisms":[44],"for":[45,126],"uncertainty":[46,55,114,130,148],"quantification.":[47],"The":[48,94,143],"thesis":[49,144],"compares":[50],"two":[51,77,159],"distinct":[52],"approaches":[53],"estimation:":[56],"Bayesian":[57,156],"approximation":[58,157],"using":[59],"Monte":[60],"Carlo":[61],"Dropout":[62],"nonparametric":[65],"Conformal":[66,117,153],"Prediction":[67],"framework.":[68],"These":[69],"methods":[70],"are":[71],"applied":[72],"predictions":[74],"generated":[75],"by":[76,151],"convolutional":[78],"network":[80],"architectures,":[81],"H-CNN":[82,98],"VGG16,":[83],"GoogLeNet,":[85],"trained":[86],"on":[87],"image":[89],"benchmark":[91],"dataset":[92],"Fashion-MNIST.":[93],"results":[95,110],"highlight":[96],"that":[97,123],"VGG16":[99],"achieves":[100],"higher":[101],"accuracy":[102],"but":[103],"tends":[104],"overconfident,":[107],"while":[108],"GoogLeNet":[109],"better":[112],"calibrated":[113],"estimation.":[115],"Moreover,":[116],"Predictions":[118,154],"provide":[119],"valid":[120],"prediction":[121],"sets":[122],"compensate":[125],"unreliable":[127],"or":[128],"misleading":[129],"estimations.":[131],"As":[132],"a":[133,137,164,172],"result,":[134],"it":[135],"is":[136],"valuable":[138],"approach":[139],"high-risk":[141],"settings.":[142],"contributes":[145],"evaluating":[147],"estimation":[149],"techniques":[150],"comparing":[152],"over":[158],"different":[160],"architectures.":[161],"It":[162],"provides":[163],"deeper":[165],"understanding":[166],"need":[169],"assess":[171],"model\u2019s":[173],"performance":[174],"beyond":[175],"its":[176],"accuracy.":[177]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7081697980","counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-10T00:00:00"}
