{"id":"https://openalex.org/W4385422543","doi":"https://doi.org/10.1007/s10489-023-04745-8","title":"Hierarchical multi-scale parametric optimization of deep neural networks","display_name":"Hierarchical multi-scale parametric optimization of deep neural networks","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385422543","doi":"https://doi.org/10.1007/s10489-023-04745-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-023-04745-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-023-04745-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-023-04745-8.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-023-04745-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067312405","display_name":"Sushen Zhang","orcid":"https://orcid.org/0000-0003-0004-2510"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sushen Zhang","raw_affiliation_strings":["Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090195152","display_name":"Vassilios S. Vassiliadis","orcid":"https://orcid.org/0000-0002-5415-7551"},"institutions":[{"id":"https://openalex.org/I4210132206","display_name":"Simulation Solutions (United Kingdom)","ror":"https://ror.org/03f4xfe90","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210132206"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vassilios S. Vassiliadis","raw_affiliation_strings":["Cambridge Simulation Solutions LTD., Waterbeach, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Simulation Solutions LTD., Waterbeach, Cambridge, UK","institution_ids":["https://openalex.org/I4210132206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081621271","display_name":"Bogdan Dorneanu","orcid":"https://orcid.org/0000-0003-3553-6625"},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bogdan Dorneanu","raw_affiliation_strings":["LS Prozess- Und Anlagentechnik, Brandenburg University of Technology Cottbus-Senftenberg, Cottbus, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3553-6625","affiliations":[{"raw_affiliation_string":"LS Prozess- Und Anlagentechnik, Brandenburg University of Technology Cottbus-Senftenberg, Cottbus, Germany","institution_ids":["https://openalex.org/I51783024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044751389","display_name":"Harvey Arellano\u2010Garc\u00eda","orcid":"https://orcid.org/0000-0002-8297-0232"},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Harvey Arellano-Garcia","raw_affiliation_strings":["LS Prozess- Und Anlagentechnik, Brandenburg University of Technology Cottbus-Senftenberg, Cottbus, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LS Prozess- Und Anlagentechnik, Brandenburg University of Technology Cottbus-Senftenberg, Cottbus, Germany","institution_ids":["https://openalex.org/I51783024"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081621271"],"corresponding_institution_ids":["https://openalex.org/I51783024"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.1512,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.32355292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"53","issue":"21","first_page":"24963","last_page":"24990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.996999979019165,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8836427927017212},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.7896369695663452},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7262212038040161},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.6576346158981323},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6314007639884949},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5999029278755188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544744610786438},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46505293250083923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44954201579093933},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4140145182609558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06910043954849243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8836427927017212},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.7896369695663452},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7262212038040161},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.6576346158981323},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6314007639884949},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5999029278755188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544744610786438},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46505293250083923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44954201579093933},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4140145182609558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06910043954849243},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10489-023-04745-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-023-04745-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-023-04745-8.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/358462","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/358462","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/4c3e57fb-0a8e-4b68-94a4-4e6a40edfef7/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10489-023-04745-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-023-04745-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-023-04745-8.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321846","display_name":"Cambridge Overseas Trust","ror":"https://ror.org/05sprqy15"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385422543.pdf"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1975655605","https://openalex.org/W1995385635","https://openalex.org/W2056116149","https://openalex.org/W2083844448","https://openalex.org/W2091602214","https://openalex.org/W2240067561","https://openalex.org/W2567089576","https://openalex.org/W2570599740","https://openalex.org/W2657631929","https://openalex.org/W2754168482","https://openalex.org/W2765369554","https://openalex.org/W2767471303","https://openalex.org/W2770653895","https://openalex.org/W2900502882","https://openalex.org/W2901542160","https://openalex.org/W2905409531","https://openalex.org/W2909324897","https://openalex.org/W2911730826","https://openalex.org/W2922004937","https://openalex.org/W2924982348","https://openalex.org/W2942231644","https://openalex.org/W2956993163","https://openalex.org/W2973136764","https://openalex.org/W2981266844","https://openalex.org/W2989569745","https://openalex.org/W2990283237","https://openalex.org/W2995140071","https://openalex.org/W3004543888","https://openalex.org/W3013514766","https://openalex.org/W3016391357","https://openalex.org/W3019321633","https://openalex.org/W3024761859","https://openalex.org/W3025887512","https://openalex.org/W3035038335","https://openalex.org/W3042513416","https://openalex.org/W3043278179","https://openalex.org/W3093932484","https://openalex.org/W3097202692","https://openalex.org/W3102775700","https://openalex.org/W3105310408","https://openalex.org/W3105666955","https://openalex.org/W3107512664","https://openalex.org/W3119156582","https://openalex.org/W3120975485","https://openalex.org/W3130503102","https://openalex.org/W3134434558","https://openalex.org/W3137392741","https://openalex.org/W3140854437","https://openalex.org/W3141285120","https://openalex.org/W3153202096","https://openalex.org/W3158764126","https://openalex.org/W3185768356","https://openalex.org/W3186197713","https://openalex.org/W3194668998","https://openalex.org/W3196155180","https://openalex.org/W3209340886","https://openalex.org/W3211127556","https://openalex.org/W3211891555","https://openalex.org/W4205912466","https://openalex.org/W4206016550","https://openalex.org/W4210678178","https://openalex.org/W4210992897","https://openalex.org/W4212861066","https://openalex.org/W4220829081","https://openalex.org/W4280503334","https://openalex.org/W4285043289","https://openalex.org/W4285305347","https://openalex.org/W4286251224","https://openalex.org/W4296311529","https://openalex.org/W4308731558","https://openalex.org/W4309721814","https://openalex.org/W4324057834","https://openalex.org/W6925421714"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W1535694475","https://openalex.org/W1965562977","https://openalex.org/W2135804779","https://openalex.org/W2093953062","https://openalex.org/W1554143855","https://openalex.org/W1529374794","https://openalex.org/W2046837923","https://openalex.org/W2393503779"],"abstract_inverted_index":{"Abstract":[0,216],"Traditionally,":[1],"sensitivity":[2,24,44],"analysis":[3,111],"has":[4],"been":[5],"utilized":[6],"to":[7,14,127,135,150,180,207],"determine":[8],"the":[9,21,61,85,91,102,118,158,162,175,190],"importance":[10],"of":[11,23,47,65,211],"input":[12],"variables":[13],"a":[15,29,32,38,69,170,195],"deep":[16],"neural":[17,120,205],"network":[18,30,50,93,121,131],"(DNN).":[19],"However,":[20],"quantification":[22],"for":[25,41,117,166,184,202],"each":[26],"neuron":[27,43,66],"in":[28,45,130],"presents":[31],"significant":[33],"challenge.":[34],"In":[35],"this":[36,96],"article,":[37],"selective":[39],"method":[40,88],"calculating":[42],"layers":[46,77],"neurons":[48,80],"concerning":[49],"output":[51],"is":[52,74,125,178],"proposed.":[53],"This":[54,106,143],"approach":[55,98,177],"incorporates":[56],"scaling":[57],"factors":[58],"that":[59,89],"facilitate":[60],"evaluation":[62],"and":[63,112,137,197],"comparison":[64],"importance.":[67],"Additionally,":[68],"hierarchical":[70],"multi-scale":[71],"optimization":[72,132,172,200],"framework":[73,124,193],"proposed,":[75],"where":[76],"with":[78,157],"high-importance":[79],"are":[81],"selectively":[82],"optimized.":[83],"Unlike":[84],"traditional":[86],"backpropagation":[87,159],"optimizes":[90],"whole":[92],"at":[94],"once,":[95],"alternative":[97,144],"focuses":[99],"on":[100],"optimizing":[101],"more":[103,182],"important":[104],"layers.":[105],"paper":[107],"provides":[108],"fundamental":[109],"theoretical":[110],"motivating":[113],"case":[114],"study":[115],"results":[116,188],"proposed":[119,176,191],"treatment.":[122],"The":[123],"shown":[126],"be":[128,181],"effective":[129],"when":[133],"applied":[134],"simulated":[136],"UCI":[138],"Machine":[139],"Learning":[140],"Repository":[141],"datasets.":[142],"training":[145,203],"generates":[146],"local":[147],"minima":[148],"close":[149],"or":[151],"even":[152],"better":[153],"than":[154],"those":[155],"obtained":[156],"method,":[160],"utilizing":[161],"same":[163],"starting":[164],"points":[165],"comparative":[167],"purposes":[168],"within":[169],"multi-start":[171],"procedure.":[173],"Moreover,":[174],"observed":[179],"efficient":[183],"large-scale":[185],"DNNs.":[186],"These":[187],"validate":[189],"algorithmic":[192],"as":[194],"rigorous":[196],"robust":[198],"new":[199],"methodology":[201],"(fitting)":[204],"networks":[206],"input/output":[208],"data":[209],"series":[210],"any":[212],"given":[213],"system.":[214],"Graphical":[215]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}