{"id":"https://openalex.org/W4409536746","doi":"https://doi.org/10.1109/lats65346.2025.10963963","title":"Improving CNN Runtime Robustness Against Soft Errors by Dropout Layer Optimization","display_name":"Improving CNN Runtime Robustness Against Soft Errors by Dropout Layer Optimization","publication_year":2025,"publication_date":"2025-03-11","ids":{"openalex":"https://openalex.org/W4409536746","doi":"https://doi.org/10.1109/lats65346.2025.10963963"},"language":"en","primary_location":{"id":"doi:10.1109/lats65346.2025.10963963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lats65346.2025.10963963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 26th Latin American Test Symposium (LATS)","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/A5006252702","display_name":"Robert Limas Sierra","orcid":"https://orcid.org/0000-0001-5206-3757"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Robert Limas Sierra","raw_affiliation_strings":["Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116539420","display_name":"Giuseppe Esposito","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Esposito","raw_affiliation_strings":["Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046650816","display_name":"Juan-David Guerrero-Balaguera","orcid":"https://orcid.org/0000-0001-6852-2372"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Juan-David Guerrero-Balaguera","raw_affiliation_strings":["Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107558399","display_name":"Josie E. Rodriguez Condia","orcid":"https://orcid.org/0000-0001-5957-5624"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Josie E. Rodriguez Condia","raw_affiliation_strings":["Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058555274","display_name":"M. Sonza Reorda","orcid":"https://orcid.org/0000-0003-2899-7669"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Sonza Reorda","raw_affiliation_strings":["Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006252702"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03828693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9914000034332275,"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":0.9914000034332275,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8076168298721313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445195913314819},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5435585379600525},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4519391655921936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13558822870254517},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12625008821487427},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.06304782629013062}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8076168298721313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445195913314819},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5435585379600525},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4519391655921936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13558822870254517},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12625008821487427},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.06304782629013062},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lats65346.2025.10963963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lats65346.2025.10963963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 26th Latin American Test Symposium (LATS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2152652532","https://openalex.org/W2194775991","https://openalex.org/W2921934355","https://openalex.org/W2963989532","https://openalex.org/W2982083293","https://openalex.org/W3047918252","https://openalex.org/W3090586977","https://openalex.org/W3128598968","https://openalex.org/W3171842021","https://openalex.org/W3184263515","https://openalex.org/W4251213825","https://openalex.org/W4297337546","https://openalex.org/W4328028948","https://openalex.org/W4387064050","https://openalex.org/W4399119842","https://openalex.org/W4399144004","https://openalex.org/W6745889759","https://openalex.org/W6790814326"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W1987310671","https://openalex.org/W2952088488"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"shown":[5],"exceptional":[6],"effectiveness":[7],"in":[8,63,76],"complex":[9],"and":[10,16,21,28,34,44,60],"data-intensive":[11],"domains":[12],"such":[13],"as":[14],"image":[15],"video":[17],"processing,":[18],"conversational":[19],"systems,":[20],"healthcare.":[22],"Moreover,":[23],"sectors":[24],"like":[25],"High-Performance":[26],"Computing":[27],"safety-critical":[29],"applications,":[30],"including":[31],"automotive,":[32],"aerospace,":[33],"autonomous":[35],"robotics,":[36],"impose":[37],"stringent":[38],"requirements":[39],"on":[40,92],"energy":[41],"efficiency,":[42],"performance,":[43],"robustness.":[45],"However,":[46],"modern":[47],"semiconductor":[48],"technologies":[49],"are":[50],"increasingly":[51],"vulnerable":[52],"to":[53,126,129,143,148],"faults,":[54],"which":[55],"can":[56,116,141],"degrade":[57],"CNN":[58,82,96,122],"performance":[59],"potentially":[61],"result":[62],"catastrophic":[64],"failures.":[65],"This":[66],"work":[67],"explores":[68],"the":[69,78,111,118],"impact":[70],"of":[71,81,121,146],"regularization":[72],"techniques":[73],"(dropout":[74],"layer)":[75],"enhancing":[77],"inference":[79],"robustness":[80,120],"models":[83,123],"against":[84],"soft":[85,89,133],"errors.":[86],"We":[87],"analyzed":[88],"error":[90,134],"impacts":[91],"five":[93],"widely":[94],"adopted":[95],"architectures,":[97],"each":[98],"trained":[99],"with":[100],"ten":[101],"different":[102],"dropout":[103,112],"rates.":[104],"Our":[105],"experimental":[106],"results":[107],"reveal":[108],"that":[109],"optimizing":[110],"rate":[113],"during":[114],"training":[115],"improve":[117],"in-field":[119],"by":[124],"up":[125,147],"12%":[127],"compared":[128],"baseline":[130],"configurations":[131],"under":[132],"conditions.":[135],"Additionally,":[136],"fine-tuning":[137],"this":[138],"architectural":[139],"parameter":[140],"lead":[142],"accurary":[144],"improvements":[145],"10%.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}