{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:50:06Z","timestamp":1784800206955,"version":"3.55.0"},"reference-count":113,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP150100294"],"award-info":[{"award-number":["DP150100294"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP150104251"],"award-info":[{"award-number":["DP150104251"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210101682"],"award-info":[{"award-number":["DP210101682"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-19-2-0501"],"award-info":[{"award-number":["FA8750-19-2-0501"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/mci.2022.3155327","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T19:35:20Z","timestamp":1649878520000},"page":"29-48","source":"Crossref","is-referenced-by-count":682,"title":["Hands-On Bayesian Neural Networks\u2014A Tutorial for Deep Learning Users"],"prefix":"10.1109","volume":"17","author":[{"given":"Laurent Valentin","family":"Jospin","sequence":"first","affiliation":[{"name":"University of Western Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[{"name":"Murdoch University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[{"name":"University of Western Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wray","family":"Buntine","sequence":"additional","affiliation":[{"name":"Murdoch University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"University of Western Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011141724916"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3847\/1538-3881\/ab2390"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.883010"},{"key":"ref32","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"kendall","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst (NIPS’17)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.7.1341"},{"key":"ref30","first-page":"1184","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","volume":"80","author":"depeweg","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1029\/2008WR007030"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2006.08.004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/15732479.2014.951867"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2020.113246"},{"key":"ref28","first-page":"13,991","article-title":"Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift","author":"ovadia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"Being Bayesian, even just a bit, fixes overconfidence in ReLU networks","author":"kristiadi","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref22","article-title":"What are Bayesian neural network posteriors really like?","author":"izmailov","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref24","article-title":"Stochastic gradient VB and the variational auto-encoder","volume":"19","author":"kingma","year":"0","journal-title":"Proc 2nd Int Conf Learn Representations ICLR"},{"key":"ref23","article-title":"Bayesian convolutional neural networks with Bernoulli approximate variational inference","author":"gal","year":"0","journal-title":"Proc 4th Int Conf Learn Representations (ICLR) Workshop Track"},{"key":"ref101","article-title":"Towards calibrated and scalable uncertainty representations for neural networks","author":"seedat","year":"2019"},{"key":"ref26","article-title":"On the validity of Bayesian neural networks for uncertainty estimation","author":"mitros","year":"0","journal-title":"Proc AICS"},{"key":"ref100","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref25","author":"robert","year":"2007","journal-title":"The Bayesian Choice From Decision-Theoretic Foundations to Computational Implementation"},{"key":"ref50","author":"gelman","year":"2020","journal-title":"Prior choice recommendations"},{"key":"ref51","article-title":"Prior choice affects ability of Bayesian neural networks to identify unknowns","author":"silvestro","year":"2020"},{"key":"ref59","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"sohn","year":"2020"},{"key":"ref58","article-title":"On information regularization","author":"tommi","year":"0","journal-title":"Proc 19th UAI"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref56","first-page":"1196","article-title":"Learning with noisy labels","author":"natarajan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods","author":"qi","year":"2019"},{"key":"ref54","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref53","article-title":"Bayesian inference over the Stiefel manifold via the Givens representation","author":"pourzanjani","year":"2017"},{"key":"ref52","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0209-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2788044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-017-1317-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2836917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00098-8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v076.i01"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/17-BA1082"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/088342304000000099"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1613\/jair.62"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref47","article-title":"Flipout: Efficient pseudo-independent weight perturbations on mini-batches","author":"wen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","article-title":"Bayesian generative active deep learning","author":"tran","year":"2019"},{"key":"ref41","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume":"70","author":"gal","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref44","first-page":"3742","article-title":"Online structured Laplace approximations for overcoming catastrophic forgetting","author":"ritter","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst (NIPS’18)"},{"key":"ref43","first-page":"363","article-title":"A Bayesian approach to on-line learning","author":"opper","year":"1998","journal-title":"On-Line Learning on Neural Networks"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032602"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2954885"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref74","article-title":"Recasting gradient-based meta-learning as hierarchical Bayes","author":"grant","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref75","first-page":"1476","article-title":"S4L: Self-supervised semi-supervised learning","author":"beyer","year":"0","journal-title":"Proc 2019 IEEE\/CVF Int Conf Comput Vis (ICCV)"},{"key":"ref78","first-page":"1515","article-title":"On Markov Chain Monte Carlo methods for tall data","volume":"18","author":"bardenet","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref79","article-title":"Explaining the Gibbs sampler","author":"george","year":"1992","journal-title":"Amer Statist"},{"key":"ref60","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"belkin","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.535"},{"key":"ref61","first-page":"2649","article-title":"Bayesian co-training","volume":"12","author":"yu","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref63","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"3","author":"lee","year":"0","journal-title":"Proc Workshop Challenges Representation Learn ICML"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-018-0702-9"},{"key":"ref65","article-title":"MultiMix: A robust data augmentation strategy for cross-lingual NLP","author":"bari","year":"0","journal-title":"Proc ICML"},{"key":"ref66","first-page":"416","article-title":"Vicinal risk minimization","author":"chapelle","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","article-title":"Unsupervised data augmentation","author":"xie","year":"2019"},{"key":"ref68","article-title":"Meta-learning in neural networks: A survey","author":"hospedales","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3194085.3194087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref1","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2013"},{"key":"ref109","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref95","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume":"48","author":"gal","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref108","first-page":"3438","article-title":"Bayesian dark knowledge","volume":"2","author":"korattikara","year":"0","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref94","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102457"},{"key":"ref93","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref106","article-title":"On last-layer algorithms for classification: Decoupling representation from uncertainty estimation","author":"brosse","year":"2020"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref105","article-title":"The relevance of Bayesian layer positioning to model uncertainty in deep Bayesian active learning","author":"zeng","year":"2018"},{"key":"ref91","first-page":"1613","article-title":"Weight uncertainty in neural network","volume":"37","author":"blundell","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref104","article-title":"Uncertainty in neural networks: Approximately Bayesian ensembling","author":"pearce","year":"0","journal-title":"Proc AISTATS"},{"key":"ref90","first-page":"1861","article-title":"Probabilistic backpropagation for scalable learning of Bayesian neural networks","volume":"37","author":"hern\u00e1ndez-lobato","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref103","first-page":"2611","article-title":"Fast and scalable Bayesian deep learning by weight-perturbation in Adam","volume":"80","author":"khan","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref102","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref111","first-page":"5190","article-title":"Adversarial distillation of Bayesian neural network posteriors","volume":"80","author":"wang","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.4467\/20838476SI.16.004.6185"},{"key":"ref110","article-title":"Why distillation helps: A statistical perspective","author":"menon","year":"2020"},{"key":"ref98","first-page":"1392","article-title":"Unlabelled data improves Bayesian uncertainty calibration under covariate shift","volume":"119","author":"chan","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref99","first-page":"4873","article-title":"Stochastic gradient descent as approximate Bayesian inference","volume":"18","author":"mandt","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref96","first-page":"2052","article-title":"Dropout inference in Bayesian neural networks with alpha-divergences","volume":"70","author":"li","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref97","first-page":"2019","article-title":"Variational Bayesian dropout: pitfalls and fixes","volume":"80","author":"hron","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref10","first-page":"45","author":"goan","year":"2020","journal-title":"Bayesian Neural Networks An Introduction and Survey"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3409383"},{"key":"ref12","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","author":"wilson","year":"2020"},{"key":"ref13","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-89267-4"},{"key":"ref15","first-page":"1321","article-title":"On calibration of modern neural network","volume":"70","author":"guo","year":"0","journal-title":"Proc 34th Int Conf Mach Learn (ICML’17)"},{"key":"ref16","article-title":"Measuring calibration in deep learning","author":"nixon","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR) Workshops"},{"key":"ref82","first-page":"1593","article-title":"The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo","volume":"15","author":"hoffman","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref17","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"0","journal-title":"Proc 5th Int Conf Learn Representations (ICLR) Conf Track Proc"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1201\/b12207"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/075450a0"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref113","first-page":"2796","article-title":"Accurate uncertainties for deep learning using calibrated regression","volume":"80","author":"kuleshov","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.1995.10476177"},{"key":"ref89","first-page":"13,153","article-title":"A simple baseline for Bayesian uncertainty in deep learning","author":"maddox","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref85","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"hoffman","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref86","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","first-page":"507","article-title":"Propagation algorithms for variational Bayesian learning","author":"ghahramani","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref88","article-title":"A scalable laplace approximation for neural networks","author":"ritter","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10207\/9756588\/09756596.pdf?arnumber=9756596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T18:11:46Z","timestamp":1682100706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9756596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":113,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mci.2022.3155327","relation":{},"ISSN":["1556-603X","1556-6048"],"issn-type":[{"value":"1556-603X","type":"print"},{"value":"1556-6048","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}