{"id":"https://openalex.org/W2920700019","doi":"https://doi.org/10.48550/arxiv.1903.00405","title":"Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines","display_name":"Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines","publication_year":2019,"publication_date":"2019-02-21","ids":{"openalex":"https://openalex.org/W2920700019","doi":"https://doi.org/10.48550/arxiv.1903.00405","mag":"2920700019"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1903.00405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.00405","pdf_url":"https://arxiv.org/pdf/1903.00405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.00405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chowdhury, Aritra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chowdhury, Aritra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051863472","display_name":"Malik Magdon\u2010Ismail","orcid":"https://orcid.org/0000-0001-7327-7770","observed_orcids":["https://orcid.org/0000-0001-7327-7770"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Magdon-Ismail, Malik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073676361","display_name":"B\u00fclent Yener","orcid":"https://orcid.org/0000-0003-3989-6097","observed_orcids":["https://orcid.org/0000-0003-3989-6097"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yener, Bulent","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":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9990000128746033,"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":0.9990000128746033,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00039999998989515007,"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":9.999999747378752e-05,"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/error-propagation","display_name":"error propagation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/machine-learning-pipelines","display_name":"machine learning pipelines","score":0.9810000061988831},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8809999823570251},{"id":"https://openalex.org/keywords/algorithm-selection","display_name":"algorithm selection","score":0.781000018119812},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.996999979019165},{"id":"https://openalex.org/keywords/random-search","display_name":"random search","score":0.8009999990463257},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.9959999918937683},{"id":"https://openalex.org/keywords/grid-search","display_name":"grid search","score":0.9869999885559082}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8465620279312134},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.809908390045166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140899896621704},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6933506727218628},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6040152907371521},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5714700222015381},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5226606726646423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088896751403809},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.44273507595062256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3918360769748688},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2072872519493103},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09297344088554382},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"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":2,"locations":[{"id":"pmh:oai:arXiv.org:1903.00405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.00405","pdf_url":"https://arxiv.org/pdf/1903.00405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.1903.00405","doi":"https://doi.org/10.48550/arxiv.1903.00405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.00405","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.00405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.00405","pdf_url":"https://arxiv.org/pdf/1903.00405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1529817821","https://openalex.org/W1686810756","https://openalex.org/W2001141328","https://openalex.org/W2089468765","https://openalex.org/W2097998348","https://openalex.org/W2102539288","https://openalex.org/W2106411961","https://openalex.org/W2108598243","https://openalex.org/W2113207845","https://openalex.org/W2124833098","https://openalex.org/W2126563020","https://openalex.org/W2131241448","https://openalex.org/W2183341477","https://openalex.org/W2200000192","https://openalex.org/W2253429366","https://openalex.org/W2276735006","https://openalex.org/W2304209433","https://openalex.org/W2309832917","https://openalex.org/W2346115250","https://openalex.org/W2462290730","https://openalex.org/W2597603852","https://openalex.org/W2911964244","https://openalex.org/W2947123069","https://openalex.org/W2963233958","https://openalex.org/W2963815651","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W2920215886","https://openalex.org/W4283794871","https://openalex.org/W6910132971","https://openalex.org/W2948038809","https://openalex.org/W3179950556","https://openalex.org/W3180849793","https://openalex.org/W4408063066","https://openalex.org/W2997201826","https://openalex.org/W6998721297","https://openalex.org/W3010924360"],"abstract_inverted_index":{"Data":[0],"science":[1],"relies":[2],"on":[3,147],"pipelines":[4,53,231],"that":[5,22,177,203],"are":[6],"organized":[7],"in":[8,58,92,140,170,232,241],"the":[9,47,61,66,79,87,93,118,126,129,141,157,164,171,197,246],"form":[10],"of":[11,18,33,55,60,89,105,120,125,131,135,234,245],"interdependent":[12],"computational":[13,106,165],"steps.":[14,62],"Each":[15,30],"step":[16],"consists":[17,32],"various":[19],"candidate":[20],"algorithms":[21,57,108,137,167],"maybe":[23],"used":[24,194,220],"for":[25],"performing":[26],"a":[27,43,83,114,132],"particular":[28],"function.":[29],"algorithm":[31,178],"several":[34],"hyperparameters.":[35,110],"Algorithms":[36],"and":[37,77,109,153,160,168,180,189,200,202,228],"hyperparameters":[38,169],"must":[39],"be":[40,193,219],"optimized":[41],"as":[42],"whole":[44],"to":[45,75,85,101,116,195,208,224],"produce":[46],"best":[48],"performance.":[49],"Typical":[50],"machine":[51,226],"learning":[52,227],"consist":[54],"complex":[56],"each":[59],"Not":[63],"only":[64],"is":[65,72,206],"selection":[67,179],"process":[68],"combinatorial,":[69],"but":[70],"it":[71],"also":[73,112],"important":[74],"interpret":[76],"understand":[78,225],"pipelines.":[80,150],"We":[81,111,143,175],"propose":[82,113],"method":[84],"quantify":[86,117,156,196,209],"importance":[88],"different":[90,243],"components":[91,124,244],"pipeline,":[94],"by":[95,221],"computing":[96],"an":[97,102],"error":[98,121,158,198],"contribution":[99,159,199],"relative":[100],"agnostic":[103,152],"choice":[104],"steps,":[107,166],"methodology":[115,146,217],"propagation":[119,161],"from":[122,163],"individual":[123,236],"pipeline":[127],"with":[128],"help":[130,240],"naive":[133,154],"set":[134],"benchmark":[136],"not":[138],"involved":[139],"pipeline.":[142,174,247],"demonstrate":[144],"our":[145],"image":[148,172],"classification":[149,173],"The":[151],"methodologies":[155],"respectively":[162],"show":[176],"hyperparameter":[181],"optimization":[182,191],"methods":[183],"like":[184],"grid":[185],"search,":[186],"random":[187,204],"search":[188,205],"Bayesian":[190,214],"can":[192,218,239],"propagation,":[201],"able":[207],"them":[210],"more":[211],"accurately":[212],"than":[213],"optimization.":[215],"This":[216],"domain":[222],"experts":[223],"data":[229],"analysis":[230],"terms":[233],"their":[235],"components,":[237],"which":[238],"prioritizing":[242]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2019-03-11T00:00:00"}