{"id":"https://openalex.org/W3171363095","doi":"https://doi.org/10.1145/3448891.3448936","title":"Towards Enhancing Fault Tolerance in Neural Networks","display_name":"Towards Enhancing Fault Tolerance in Neural Networks","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3171363095","doi":"https://doi.org/10.1145/3448891.3448936","mag":"3171363095"},"language":"en","primary_location":{"id":"doi:10.1145/3448891.3448936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448891.3448936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.03103","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037812896","display_name":"Vasisht Duddu","orcid":"https://orcid.org/0000-0003-2138-4341"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I2802246343","display_name":"Regional Municipality of Waterloo","ror":"https://ror.org/04apt4x36","country_code":"CA","type":"government","lineage":["https://openalex.org/I2802246343"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vasisht Duddu","raw_affiliation_strings":["Waterloo and 288","University of WAterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waterloo and 288","institution_ids":["https://openalex.org/I2802246343"]},{"raw_affiliation_string":"University of WAterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008638246","display_name":"Dushyant Rao","orcid":"https://orcid.org/0000-0002-1372-2884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D Vijay Rao","raw_affiliation_strings":["Delhi and 288"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi and 288","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000355426","display_name":"Valentina Emilia B\u0103la\u015f","orcid":"https://orcid.org/0000-0003-0885-1283"},"institutions":[{"id":"https://openalex.org/I3021884489","display_name":"Arad County Clinical Hospital","ror":"https://ror.org/03t1qsw88","country_code":"RO","type":"healthcare","lineage":["https://openalex.org/I3021884489"]},{"id":"https://openalex.org/I64956957","display_name":"Aurel Vlaicu University of Arad","ror":"https://ror.org/05w5rsy15","country_code":"RO","type":"education","lineage":["https://openalex.org/I64956957"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Valentina Balas","raw_affiliation_strings":["Arad and 288","\u201cAurel  Vlaicu\u201d University of Arad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arad and 288","institution_ids":["https://openalex.org/I3021884489"]},{"raw_affiliation_string":"\u201cAurel  Vlaicu\u201d University of Arad","institution_ids":["https://openalex.org/I64956957"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9878000020980835,"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":0.7529917359352112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6782684326171875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6310391426086426},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5550153255462646},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.553130030632019},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.527185320854187},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5052943825721741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42455342411994934},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42101752758026123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7529917359352112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782684326171875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6310391426086426},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5550153255462646},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.553130030632019},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.527185320854187},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5052943825721741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42455342411994934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42101752758026123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3448891.3448936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448891.3448936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.03103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03103","pdf_url":"https://arxiv.org/pdf/1907.03103","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},{"id":"mag:3171363095","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.03103.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.03103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.03103","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.03103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03103","pdf_url":"https://arxiv.org/pdf/1907.03103","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3171363095.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1987856988","https://openalex.org/W2051513586","https://openalex.org/W2098137815","https://openalex.org/W2099471712","https://openalex.org/W2111406701","https://openalex.org/W2113502831","https://openalex.org/W2123422798","https://openalex.org/W2139072039","https://openalex.org/W2139318413","https://openalex.org/W2144784023","https://openalex.org/W2145249131","https://openalex.org/W2148605318","https://openalex.org/W2149431208","https://openalex.org/W2149593503","https://openalex.org/W2152692509","https://openalex.org/W2166767167","https://openalex.org/W2519070763","https://openalex.org/W2589859332","https://openalex.org/W2604319603","https://openalex.org/W2606321545","https://openalex.org/W2748528844","https://openalex.org/W2749412917","https://openalex.org/W2767260595","https://openalex.org/W2894972989","https://openalex.org/W2904958088","https://openalex.org/W2945994301","https://openalex.org/W2952825952","https://openalex.org/W2963334011","https://openalex.org/W2964866569","https://openalex.org/W2982636379","https://openalex.org/W2989817299","https://openalex.org/W3009818168"],"related_works":["https://openalex.org/W2954580816","https://openalex.org/W3190315974","https://openalex.org/W2103745410","https://openalex.org/W2774611252","https://openalex.org/W205793414","https://openalex.org/W2088572182","https://openalex.org/W2077700203","https://openalex.org/W3016866710","https://openalex.org/W3092600489","https://openalex.org/W2540833927","https://openalex.org/W2146555798","https://openalex.org/W1678611306","https://openalex.org/W2908935113","https://openalex.org/W2894461463","https://openalex.org/W2890821718","https://openalex.org/W3184415262","https://openalex.org/W2765284480","https://openalex.org/W3011102476","https://openalex.org/W1966635105","https://openalex.org/W3205135396"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"Accelerators":[2],"and":[3,47,71,98,216,236,288,295],"Neuromorphic":[4],"hardware,":[5],"used":[6],"in":[7,18,23,28,77,180,318],"many":[8],"real-time":[9],"safety-critical":[10],"applications,":[11],"are":[12,121],"prone":[13],"to":[14,110,123,200,231,305,312],"faults":[15,309],"that":[16,37,301],"manifest":[17],"the":[19,63,112,125,128,149,157,163,166,170,181,197,205,214,228,233,246,257,264,298],"form":[20],"of":[21,54,127,148,156,169,183,297],"errors":[22],"Neural":[24,29,55,81,184],"Networks.":[25],"Fault":[26],"Tolerance":[27],"Networks":[30,56,185],"is":[31,83,160,173,251,254,273,293],"a":[32,67,80,90,99,104,116,136,193,210,223,239],"critical":[33],"attribute":[34],"for":[35,41,204,261],"applications":[36],"require":[38],"reliable":[39],"computation":[40],"long":[42],"duration":[43],"such":[44],"as":[45,85,310],"IoT":[46],"mobile":[48],"devices.":[49],"The":[50,189,219,267,290],"inherent":[51],"fault":[52],"tolerance":[53,304],"can":[57],"be":[58],"improved":[59],"with":[60,93,103,141,186,192,222,238,256,278],"regularization,":[61],"however,":[62],"current":[64],"techniques":[65],"exhibit":[66],"trade-off":[68],"between":[69,213],"generalization":[70],"classification":[72,225,265,285,319],"accuracy.":[73,320],"To":[74],"this":[75,78,134],"extent,":[76],"work,":[79,135],"Network":[82,159],"modelled":[84],"two":[86,138,176,269],"distinct":[87],"functional":[88,130],"components:":[89],"Feature":[91,150,171,198,229,248],"Extractor":[92,151,172,199,230],"an":[94],"unsupervised":[95,146,167],"learning":[96,106,119],"objective":[97,120,143],"Fully":[100,258],"Connected":[101,259],"Classifier":[102,158,260],"supervised":[105,118,154],"objective.":[107],"Traditional":[108],"approaches":[109],"train":[111],"entire":[113],"network":[114,299],"using":[115,175],"single":[117],"insufficient":[122],"achieve":[124],"objectives":[126],"individual":[129],"goals":[131],"optimally.":[132],"In":[133,162,243],"novel":[137],"phase":[139,270],"framework":[140,292],"multi-criteria":[142],"function":[144],"combining":[145],"training":[147,155,168,271],"followed":[152],"by":[153,208],"proposed.":[161],"Phase":[164,244],"I,":[165],"modeled":[174],"games":[177],"solved":[178],"simultaneously":[179],"presence":[182],"conflicting":[187],"objectives.":[188],"first":[190],"game":[191,221],"generative":[194],"model,":[195],"trains":[196],"generate":[201],"robust":[202],"features":[203],"input":[206,215],"image":[207,284],"minimizing":[209],"reconstruction":[211],"loss":[212,317],"reconstructed":[217],"image.":[218],"second":[220],"binary":[224],"network,":[226],"updates":[227],"smoothen":[232],"feature":[234],"space":[235],"match":[237],"prior":[240],"Gaussian":[241],"distribution.":[242],"II,":[245],"resultant":[247],"Extractor,":[249],"which":[250],"strongly":[252],"regularized,":[253],"combined":[255],"fine-tuning":[262],"on":[263,275,282],"task.":[266],"proposed":[268,291],"algorithm":[272],"evaluated":[274],"four":[276],"architectures":[277],"varying":[279],"model":[280],"complexity":[281],"standard":[283],"datasets:":[286],"FashionMNIST":[287],"CIFAR10.":[289],"scalable":[294],"independent":[296],"architecture":[300],"provides":[302],"superior":[303],"stuck":[306],"at":[307],"\u201c0\u201d":[308],"compared":[311],"existing":[313],"regularization":[314],"functions":[315],"without":[316]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}