{"id":"https://openalex.org/W2991229825","doi":"https://doi.org/10.1109/mlsp.2019.8918747","title":"Extended Variational Inference for Propagating Uncertainty in Convolutional Neural Networks","display_name":"Extended Variational Inference for Propagating Uncertainty in Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991229825","doi":"https://doi.org/10.1109/mlsp.2019.8918747","mag":"2991229825"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2019.8918747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2019.8918747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5068906628","display_name":"Dimah Dera","orcid":"https://orcid.org/0000-0002-7168-5858"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dimah Dera","raw_affiliation_strings":["Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045996251","display_name":"Ghulam Rasool","orcid":"https://orcid.org/0000-0001-8551-0090"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghulam Rasool","raw_affiliation_strings":["Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041401460","display_name":"Nidhal Bouaynaya","orcid":"https://orcid.org/0000-0002-8833-8414"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhal Bouaynaya","raw_affiliation_strings":["Electrical and Computer Engineering, Rowan University, Glassboro, NJ"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Rowan University, Glassboro, NJ","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068906628"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":2.1002,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90538464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.996399998664856,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9919999837875366,"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/expectation-propagation","display_name":"Expectation propagation","score":0.6958128213882446},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.6920911073684692},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6752752065658569},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6600756645202637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6179850697517395},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5389851331710815},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.4853631258010864},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.48515209555625916},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4757378101348877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45674625039100647},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4523707926273346},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.4316192865371704},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.41693738102912903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40420103073120117},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.392331600189209},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.35493141412734985},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.350055456161499},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33661872148513794},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.2969561815261841},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2862522602081299},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2832343578338623},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.20422470569610596}],"concepts":[{"id":"https://openalex.org/C2779363554","wikidata":"https://www.wikidata.org/wiki/Q5420835","display_name":"Expectation propagation","level":4,"score":0.6958128213882446},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6920911073684692},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6752752065658569},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6600756645202637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6179850697517395},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5389851331710815},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.4853631258010864},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.48515209555625916},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4757378101348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45674625039100647},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4523707926273346},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.4316192865371704},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.41693738102912903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40420103073120117},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.392331600189209},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.35493141412734985},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.350055456161499},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33661872148513794},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2969561815261841},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2862522602081299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2832343578338623},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.20422470569610596},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2019.8918747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2019.8918747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W164706946","https://openalex.org/W601603264","https://openalex.org/W1665214252","https://openalex.org/W1667165204","https://openalex.org/W1719489212","https://openalex.org/W1934021597","https://openalex.org/W1989730800","https://openalex.org/W2007339694","https://openalex.org/W2030434042","https://openalex.org/W2046245205","https://openalex.org/W2047229728","https://openalex.org/W2108677974","https://openalex.org/W2164411961","https://openalex.org/W2176412452","https://openalex.org/W2182396527","https://openalex.org/W2437421599","https://openalex.org/W2524610192","https://openalex.org/W2570685808","https://openalex.org/W2600383743","https://openalex.org/W2808181858","https://openalex.org/W2907020378","https://openalex.org/W2909241519","https://openalex.org/W2950117601","https://openalex.org/W2951266961","https://openalex.org/W2963285578","https://openalex.org/W2964339591","https://openalex.org/W3011097439","https://openalex.org/W3118608800","https://openalex.org/W4211049957","https://openalex.org/W6618476874","https://openalex.org/W6637242042","https://openalex.org/W6640231202","https://openalex.org/W6676315081","https://openalex.org/W6718624722","https://openalex.org/W6731927902","https://openalex.org/W6735443497","https://openalex.org/W6764214684","https://openalex.org/W6774910700"],"related_works":["https://openalex.org/W2913749182","https://openalex.org/W3156786002","https://openalex.org/W4298151506","https://openalex.org/W3168765527","https://openalex.org/W2734405990","https://openalex.org/W3163718425","https://openalex.org/W1569946230","https://openalex.org/W2952720608","https://openalex.org/W2991229825","https://openalex.org/W4313679788"],"abstract_inverted_index":{"Model":[0],"confidence":[1],"or":[2],"uncertainty":[3,24,47,138],"is":[4,34,70,143],"critical":[5],"in":[6,25,139],"autonomous":[7],"systems":[8],"as":[9],"they":[10],"directly":[11],"tie":[12],"to":[13,126,171],"the":[14,19,26,42,45,53,58,104,118,128,134,140,146,150,160,166],"safety":[15],"and":[16,67,109,130,162,174],"trustworthiness":[17],"of":[18,23,29,44,60,111,117,149],"system.":[20],"The":[21,38,137],"quantification":[22],"output":[27,141],"decisions":[28],"deep":[30],"neural":[31,86],"networks":[32],"(DNNs)":[33],"a":[35],"challenging":[36],"problem.":[37],"Bayesian":[39],"framework":[40,83,102],"enables":[41],"estimation":[43],"predictive":[46,151],"by":[48,145],"introducing":[49],"probability":[50],"distributions":[51,63,93],"over":[52,96],"(unknown)":[54],"network":[55,87],"weights;":[56],"however,":[57],"propagation":[59],"these":[61,112],"high-dimensional":[62],"through":[64,114,133,156],"multiple":[65],"layers":[66,116],"non-linear":[68,135],"transformations":[69],"mathematically":[71],"intractable.":[72],"In":[73],"this":[74],"work,":[75],"we":[76,154],"propose":[77],"an":[78],"extended":[79],"variational":[80],"inference":[81],"(eVI)":[82],"for":[84],"convolutional":[85,97],"(CNN)":[88],"based":[89],"on":[90,159],"tensor":[91],"Normal":[92],"(TNDs)":[94],"defined":[95],"kernels.":[98],"Our":[99],"proposed":[100],"eVI":[101],"propagates":[103],"first":[105],"two":[106],"moments":[107],"(mean":[108],"covariance)":[110],"TNDs":[113],"all":[115],"CNN.":[119],"We":[120],"employ":[121],"first-order":[122],"Taylor":[123],"series":[124],"linearization":[125],"approximate":[127],"mean":[129],"covariances":[131],"passing":[132],"activations.":[136],"decision":[142],"given":[144],"propagated":[147],"covariance":[148],"distribution.":[152],"Furthermore,":[153],"show,":[155],"extensive":[157],"simulations":[158],"MNIST":[161],"CIFAR-10":[163],"datasets,":[164],"that":[165],"CNN":[167],"becomes":[168],"more":[169],"robust":[170],"Gaussian":[172],"noise":[173],"adversarial":[175],"attacks.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}