{"id":"https://openalex.org/W4416248324","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228576","title":"Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective","display_name":"Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416248324","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228576"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5102684411","display_name":"Xueqiong Yuan","orcid":"https://orcid.org/0009-0008-4706-3099"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueqiong Yuan","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015572779","display_name":"Jipeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jipeng Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038228706","display_name":"Er\u00e7an E. Kuruo\u011flu","orcid":"https://orcid.org/0000-0002-2608-8034"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ercan Engin Kuruoglu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102684411"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.7137,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95338743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8162999749183655,"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":0.8162999749183655,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.11150000244379044,"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":0.006899999920278788,"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/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.6499000191688538},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.628000020980835},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.597000002861023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5656999945640564},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5478000044822693},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.532800018787384},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5031999945640564},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.41269999742507935}],"concepts":[{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6032999753952026},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.597000002861023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5536999702453613},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5031999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4758000075817108},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C176147448","wikidata":"https://www.wikidata.org/wiki/Q1889114","display_name":"Sensitivity analysis","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2662999927997589},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1549559066","https://openalex.org/W1567512734","https://openalex.org/W2073241381","https://openalex.org/W2080435280","https://openalex.org/W2111051539","https://openalex.org/W2120969381","https://openalex.org/W2124136621","https://openalex.org/W2194775991","https://openalex.org/W2905549570","https://openalex.org/W2963485691","https://openalex.org/W2964059111","https://openalex.org/W3116074996","https://openalex.org/W3119028141","https://openalex.org/W3177280989","https://openalex.org/W4214498565","https://openalex.org/W4221138852","https://openalex.org/W4225941155","https://openalex.org/W4402754355"],"related_works":[],"abstract_inverted_index":{"Model":[0],"uncertainty":[1,8,47,105],"quantification":[2,48],"involves":[3,87],"measuring":[4],"and":[5,18,46,95,111,115],"evaluating":[6],"the":[7,28,60,91,104,107,125],"linked":[9],"to":[10,26,68,102,124],"a":[11,23,41,50,63,72,79],"model\u2019s":[12],"predictions,":[13],"helping":[14],"assess":[15],"their":[16],"reliability":[17],"confidence.":[19],"Noise":[20,82],"injection":[21,45],"is":[22,66],"technique":[24],"used":[25],"enhance":[27],"robustness":[29],"of":[30,62,106],"neural":[31,64],"networks":[32],"by":[33],"introducing":[34],"randomness.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,77],"establish":[40],"connection":[42],"between":[43],"noise":[44,58,89],"from":[49],"Bayesian":[51,69],"standpoint.":[52],"We":[53],"theoretically":[54],"demonstrate":[55],"that":[56],"injecting":[57,88],"into":[59,90],"weights":[61],"network":[65],"equivalent":[67],"inference":[70,101],"on":[71,113],"deep":[73],"Gaussian":[74],"process.":[75],"Consequently,":[76],"introduce":[78],"Monte":[80],"Carlo":[81],"Injection":[83],"(MCNI)":[84],"method,":[85],"which":[86],"parameters":[92],"during":[93,100],"training":[94],"performing":[96],"multiple":[97],"forward":[98],"propagations":[99],"estimate":[103],"prediction.":[108],"Through":[109],"simulation":[110],"experiments":[112],"regression":[114],"classification":[116],"tasks,":[117],"our":[118],"method":[119],"demonstrates":[120],"superior":[121],"performance":[122],"compared":[123],"baseline":[126],"model.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}