{"id":"https://openalex.org/W4393564741","doi":"https://doi.org/10.1117/12.3006909","title":"Evaluating the performance of hyperparameters for unbiased and fair machine learning","display_name":"Evaluating the performance of hyperparameters for unbiased and fair machine learning","publication_year":2024,"publication_date":"2024-04-02","ids":{"openalex":"https://openalex.org/W4393564741","doi":"https://doi.org/10.1117/12.3006909"},"language":"en","primary_location":{"id":"doi:10.1117/12.3006909","doi":"https://doi.org/10.1117/12.3006909","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.3006909","pdf_url":null,"source":{"id":"https://openalex.org/S4363607561","display_name":"SPIE Medical Imaging: Image Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Medical Imaging 2024: Image Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5009773815","display_name":"Vy Bui","orcid":"https://orcid.org/0000-0001-5749-3756","observed_orcids":["https://orcid.org/0000-0001-5749-3756"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vy Bui","raw_affiliation_strings":["National Institutes of Health (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health (United States)","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432192","display_name":"Hang Yu","orcid":"https://orcid.org/0009-0000-4624-1123","observed_orcids":["https://orcid.org/0009-0000-4624-1123"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["National Institutes of Health (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health (United States)","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066535118","display_name":"Karthik Kantipudi","orcid":"https://orcid.org/0000-0002-6423-1647","observed_orcids":["https://orcid.org/0000-0002-6423-1647"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Kantipudi","raw_affiliation_strings":["National Institutes of Health (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health (United States)","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051027046","display_name":"Ziv Yaniv","orcid":"https://orcid.org/0000-0003-0315-7727","observed_orcids":["https://orcid.org/0000-0003-0315-7727"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziv Yaniv","raw_affiliation_strings":["National Institutes of Health (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health (United States)","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035100758","display_name":"Stefan Jaeger","orcid":"https://orcid.org/0000-0001-6877-4318","observed_orcids":["https://orcid.org/0000-0001-6877-4318"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Jaeger","raw_affiliation_strings":["National Institutes of Health (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institutes of Health (United States)","institution_ids":["https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1299303238"],"apc_list":null,"apc_paid":null,"fwci":0.3054,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50447172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.6333000063896179,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6333000063896179,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2815000116825104,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.019899999722838402,"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/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.8519999980926514},{"id":"https://openalex.org/keywords/adam-optimizer","display_name":"Adam optimizer","score":0.9990000128746033},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.6700000166893005},{"id":"https://openalex.org/keywords/learning-rate","display_name":"learning rate","score":0.7429999709129333},{"id":"https://openalex.org/keywords/momentum","display_name":"momentum","score":0.8970000147819519},{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.49300000071525574},{"id":"https://openalex.org/keywords/algorithmic-bias","display_name":"algorithmic bias","score":0.718999981880188},{"id":"https://openalex.org/keywords/noisy-training-data","display_name":"noisy training data","score":0.7379999756813049},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.7289999723434448},{"id":"https://openalex.org/keywords/tuberculosis-detection","display_name":"tuberculosis detection","score":0.7760000228881836},{"id":"https://openalex.org/keywords/chest-x-ray","display_name":"chest radiography","score":0.6740000247955322},{"id":"https://openalex.org/keywords/lung-segmentation","display_name":"lung segmentation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/malaria-parasite-detection","display_name":"malaria parasite detection","score":0.9010000228881836},{"id":"https://openalex.org/keywords/blood-smear-images","display_name":"blood smear images","score":0.7070000171661377},{"id":"https://openalex.org/keywords/mnist-classification","display_name":"MNIST classification","score":0.8759999871253967},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5849999785423279},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.40700000524520874},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.843999981880188}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8309557437896729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7847992181777954},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7538872957229614},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7404374480247498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087941765785217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6160169839859009},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.5971176624298096},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5901228785514832},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5670909285545349},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5445506572723389},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49535810947418213},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4222784638404846},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39280325174331665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36853861808776855},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19705545902252197},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09110647439956665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.3006909","doi":"https://doi.org/10.1117/12.3006909","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.3006909","pdf_url":null,"source":{"id":"https://openalex.org/S4363607561","display_name":"SPIE Medical Imaging: Image Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Medical Imaging 2024: Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1904878066","https://openalex.org/W2776855315","https://openalex.org/W2783699776","https://openalex.org/W2807888536","https://openalex.org/W2963208657","https://openalex.org/W2963794891","https://openalex.org/W2964744899","https://openalex.org/W3013601031","https://openalex.org/W3034995656","https://openalex.org/W3091965439","https://openalex.org/W4200409436","https://openalex.org/W4206759694","https://openalex.org/W4250685322","https://openalex.org/W4285347673","https://openalex.org/W4286210597","https://openalex.org/W4287750641","https://openalex.org/W4318240621"],"related_works":["https://openalex.org/W7128724730","https://openalex.org/W4383560294","https://openalex.org/W7151569375","https://openalex.org/W7130439013","https://openalex.org/W4411409196","https://openalex.org/W7128928815","https://openalex.org/W4221032047","https://openalex.org/W4413343163","https://openalex.org/W4414855915","https://openalex.org/W4405536469"],"abstract_inverted_index":{"Biased":[0],"outcomes":[1],"in":[2,108,118,148,152,180,207,364,385,399],"machine":[3],"learning":[4,40],"models":[5],"can":[6],"arise":[7],"due":[8],"to":[9,46,90,167,190,198,361,395],"various":[10],"factors,":[11],"including":[12],"limited":[13],"training":[14,20,25],"data,":[15,323],"imbalanced":[16],"class":[17],"distribution,":[18],"suboptimal":[19],"methodologies,":[21],"and":[22,33,42,64,84,87,112,165,216,250,261,276,342,388],"overfitting.":[23],"In":[24,122,240,264,314,367],"neural":[26],"networks":[27],"with":[28,61,67,294,300,346],"Stochastic":[29],"Gradient":[30],"Descent":[31],"(SGD)":[32],"backpropagation,":[34],"the":[35,48,68,97,113,123,128,131,136,208,211,226,241,259,265,272,291,373,377,386],"choice":[36],"of":[37,115,238,267,376],"hyperparameters":[38,60,66],"like":[39],"rate":[41],"momentum":[43],"is":[44,371],"crucial":[45],"influencing":[47],"model\u2019s":[49],"performance.":[50],"A":[51],"comprehensive":[52],"grid":[53],"search":[54],"study":[55,126,244],"was":[56,88,163,214,218,359],"conducted":[57],"using":[58,96,248,271,351],"static":[59],"standard":[62],"SGD":[63,132,143,183,231,253,275,304,328,341,381],"dynamic":[65],"Adam":[69,137,151,221,233,256,277,295,343,370],"optimizer.":[70],"The":[71],"investigation":[72],"focused":[73],"on":[74,127,225,234,258,290,321],"a":[75,145,153,177,185,235],"multifaceted":[76],"analysis":[77],"across":[78,200,282],"different":[79,283,354],"tasks":[80],"\u2014-":[81],"classification,":[82],"segmentation,":[83],"detection":[85,101,114,206,270],"\u2014":[86],"applied":[89],"four":[91],"image-based":[92],"applications:":[93],"digit":[94],"classification":[95],"MNIST":[98,129],"dataset,":[99,130,293],"tuberculosis":[100],"from":[102,353],"chest":[103,109],"X-ray":[104,110],"images,":[105,111],"lung":[106,246],"segmentation":[107,247],"malaria":[116,268],"parasites":[117],"blood":[119],"smear":[120],"images.":[121],"first":[124],"comparative":[125,243],"algorithm":[133,138],"consistently":[134],"outperformed":[135,232,255],"as":[139,161],"noise":[140,162,172,202,315,326],"levels":[141],"increased.":[142],"held":[144,382],"slight":[146],"advantage":[147,157],"accuracy":[149,188,311,320],"over":[150],"noise-free":[154],"environment.":[155],"This":[156,192],"became":[158],"more":[159,306,374],"apparent":[160],"introduced":[164],"increased":[166],"moderate":[168],"levels.":[169],"At":[170],"high":[171,288],"levels,":[173],"both":[174,286,317],"algorithms":[175],"experienced":[176],"significant":[178],"decline":[179],"performance,":[181,308],"yet":[182],"maintained":[184,305,329],"relatively":[186],"better":[187,223,333],"compared":[189],"Adam.":[191],"trend":[193],"underscored":[194],"SGD\u2019s":[195,356],"superior":[196,360,390],"ability":[197],"generalize":[199],"varying":[201,280],"conditions.":[203,284,401],"For":[204],"TB":[205],"second":[209],"application,":[210],"DenseNet121":[212],"architecture":[213],"used,":[215],"it":[217,393],"found":[219],"that":[220],"showed":[222,279,318,389],"performance":[224,358,363,391],"larger":[227],"TBX11K":[228],"dataset.":[229],"However,":[230,299],"smaller":[236],"subset":[237],"TBX11K.":[239],"third":[242],"for":[245],"COVID-19":[249],"NLM":[251],"datasets,":[252],"slightly":[254,296],"based":[257],"mean":[260],"Hausdorff":[262],"distances.":[263],"case":[266],"parasite":[269],"YOLOv8":[273],"architecture,":[274],"optimizers":[278],"performances":[281],"Initially,":[285],"achieved":[287],"accuracies":[289],"full":[292],"outperforming":[297],"SGD.":[298],"decreasing":[301],"dataset":[302],"size,":[303],"consistent":[307],"while":[309],"Adam\u2019s":[310,362],"fluctuated":[312],"significantly.":[313],"tests,":[316],"equal":[319],"clean":[322],"but":[324],"under":[325],"conditions,":[327],"higher":[330],"accuracies,":[331],"suggesting":[332],"generalization":[334,357,396],"capabilities.":[335],"Further":[336],"experiments":[337,387],"assessed":[338],"how":[339],"well":[340],"could":[344],"cope":[345],"domain":[347],"shifts,":[348],"mainly":[349],"when":[350,392],"data":[352],"countries.":[355],"these":[365],"experiments.":[366],"summary,":[368],"although":[369],"arguably":[372],"popular":[375],"two":[378],"optimization":[379],"techniques,":[380],"its":[383],"own":[384],"came":[394],"or":[397],"classifying":[398],"noisy":[400]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-04-03T00:00:00"}