{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T23:13:06Z","timestamp":1773097986053,"version":"3.50.1"},"reference-count":146,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012331","name":"Flemish Innovation and Entrepreneurship (VLAIO) through the Baekeland Ph.D. Mandate","doi-asserted-by":"publisher","award":["HBC.2019.2604"],"award-info":[{"award-number":["HBC.2019.2604"]}],"id":[{"id":"10.13039\/100012331","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3168734","type":"journal-article","created":{"date-parts":[[2022,4,21]],"date-time":"2022-04-21T19:35:08Z","timestamp":1650569708000},"page":"43703-43737","source":"Crossref","is-referenced-by-count":8,"title":["Benchmarking Scalable Predictive Uncertainty in Text Classification"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9838-3024","authenticated-orcid":false,"given":"Jordy","family":"Van Landeghem","sequence":"first","affiliation":[{"name":"Department of Computer Science, KU Leuven, Leuven, LIIR, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2640-181X","authenticated-orcid":false,"given":"Matthew","family":"Blaschko","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, ESAT-PSI, KU Leuven, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertrand","family":"Anckaert","sequence":"additional","affiliation":[{"name":"Contract.fit, Deinze, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie-Francine","family":"Moens","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KU Leuven, Leuven, LIIR, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref2","first-page":"1","article-title":"In-between uncertainty in Bayesian neural networks","volume-title":"Proc. ICML Workshop Uncertainty Robustness Deep Learn.","author":"Foong"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"key":"ref4","article-title":"Hands-on Bayesian neural networks\u2014A tutorial for deep learning users","author":"Valentin Jospin","year":"2020","journal-title":"arXiv:2007.06823"},{"key":"ref5","article-title":"Troubling trends in machine learning scholarship","author":"Lipton","year":"2018","journal-title":"arXiv:1807.03341"},{"key":"ref6","article-title":"Towards calibrated and scalable uncertainty representations for neural networks","author":"Seedat","year":"2019","journal-title":"arXiv:1911.00104"},{"key":"ref7","article-title":"The case for Bayesian deep learning","author":"Wilson","year":"2020","journal-title":"arXiv:2001.10995"},{"key":"ref8","article-title":"On the importance of strong baselines in Bayesian deep learning","author":"Mukhoti","year":"2018","journal-title":"arXiv:1811.09385"},{"key":"ref9","first-page":"1861","article-title":"Probabilistic backpropagation for scalable learning of Bayesian neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hern\u00e1ndez-Lobato"},{"key":"ref10","first-page":"234","article-title":"Uncertainty in neural networks: Approximately Bayesian ensembling","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Pearce"},{"key":"ref11","article-title":"A systematic comparison of Bayesian deep learning robustness in diabetic retinopathy tasks","author":"Filos","year":"2019","journal-title":"arXiv:1912.10481"},{"key":"ref12","first-page":"13991","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ovadia"},{"key":"ref13","first-page":"13153","article-title":"A simple baseline for Bayesian uncertainty in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Maddox"},{"key":"ref14","article-title":"Pitfalls of in-domain uncertainty estimation and ensembling in deep learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ashukha"},{"key":"ref15","article-title":"URSABench: Comprehensive benchmarking of approximate Bayesian inference methods for deep neural networks","author":"Vadera","year":"2020","journal-title":"arXiv:2007.04466"},{"key":"ref16","article-title":"Motivating the rules of the game for adversarial example research","author":"Gilmer","year":"2018","journal-title":"arXiv:1807.06732"},{"key":"ref17","first-page":"440","article-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","volume-title":"Proc. 45th Annu. Meeting Assoc. Comput. Linguistics","author":"Blitzer"},{"key":"ref18","first-page":"1","article-title":"Frustratingly easy domain adaptation","volume-title":"Proc. 45th Annu. Meeting Assoc. Comput. Linguistics","author":"Daum\u00e9"},{"key":"ref19","first-page":"1302","article-title":"Multi-domain learning: When do domains matter?","volume-title":"Proc. Joint Conf. Empirical Methods Natural Lang. Process. Comput. Natural Lang. Learn.","author":"Joshi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1040"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.603"},{"key":"ref23","article-title":"Out of distribution generalization in machine learning","author":"Arjovsky","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/534"},{"key":"ref25","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref26","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref27","article-title":"Do deep generative models know what they don\u2019t know?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nalisnick"},{"key":"ref28","first-page":"1","article-title":"Selective classification for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Geifman"},{"key":"ref29","first-page":"1396","article-title":"Failing loudly: An empirical study of methods for detecting dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rabanser"},{"key":"ref30","article-title":"A less biased evaluation of out-of-distribution sample detectors","volume-title":"Proc. BMVC","author":"Shafaei"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010274"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"ref33","article-title":"Bayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding","author":"Kendall","year":"2015","journal-title":"arXiv:1511.02680"},{"key":"ref34","first-page":"1","article-title":"Discreteness in neural natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP-IJCNLP)","author":"Mou"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref37","first-page":"806","article-title":"Learning to resolve natural language ambiguities: A unified approach","volume-title":"Proc. AAAI\/IAAI","author":"Roth"},{"key":"ref38","article-title":"Long-length legal document classification","author":"Wan","year":"2019","journal-title":"arXiv:1912.06905"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1352"},{"key":"ref40","article-title":"Multi-label text classification with a mixture model trained by EM","volume-title":"Proc. AAAI Workshop Text Learn.","author":"McCallum"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017322"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.244"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1316"},{"key":"ref44","first-page":"21199","article-title":"Uncertainty-aware self-training for few-shot text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mukherjee"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref46","first-page":"886","article-title":"Confidence measures for neural network classifiers","volume-title":"Proc. 7th Int. Conf. Inf. Process. Manage. Uncertainty Knowl. Based Syst.","author":"Zaragoza"},{"key":"ref47","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Guo"},{"key":"ref48","first-page":"222","article-title":"Maximum likelihood with bias-corrected calibration is hard-to-beat at label shift adaptation","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Shrikumar"},{"issue":"5","key":"ref49","first-page":"877","article-title":"Large automatic learning, rule extraction, and generalization","volume":"1","author":"Denker","year":"1987","journal-title":"Complex Syst."},{"key":"ref50","article-title":"Bayesian methods for adaptive models","author":"MacKay","year":"1992"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2219-3_14"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X_6_3_011"},{"key":"ref54","article-title":"A history of Bayesian neural networks","volume-title":"Proc. NIPS Workshop Bayesian Deep Learn.","author":"Ghahramani"},{"key":"ref55","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan"},{"key":"ref56","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Huang"},{"key":"ref57","first-page":"8789","article-title":"Loss surfaces, mode connectivity, and fast ensembling of DNNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Garipov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1201\/b14835"},{"key":"ref59","article-title":"Langevin dynamics as nonparametric variational inference","volume-title":"Proc. 2nd Symp. Adv. Approx. Bayesian Inference","author":"Hoffman"},{"key":"ref60","article-title":"Cyclical stochastic gradient MCMC for Bayesian deep learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref62","first-page":"9690","article-title":"Uncertainty estimation using a single deep deterministic neural network","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Van Amersfoort"},{"key":"ref63","first-page":"7498","article-title":"Simple and principled uncertainty estimation with deterministic deep learning via distance awareness","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511984679.006"},{"key":"ref65","article-title":"Batchensemble: An alternative approach to efficient ensemble and lifelong learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wen"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"ref67","first-page":"231","article-title":"Neural network ensembles, cross validation, and active learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"7","author":"Krogh"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5849"},{"key":"ref69","article-title":"Collective learning by ensembles of altruistic diversifying neural networks","author":"Brazowski","year":"2020","journal-title":"arXiv:2006.11671"},{"key":"ref70","first-page":"3581","article-title":"Concrete dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gal"},{"key":"ref71","article-title":"Risk versus uncertainty in deep learning: Bayes, bootstrap and the dangers of dropout","volume-title":"Proc. NIPS Workshop Bayesian Deep Learn.","volume":"192","author":"Osband"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2019.106816"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref75","first-page":"1184","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Depeweg"},{"key":"ref76","first-page":"1","article-title":"Understanding measures of uncertainty for adversarial example detection","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Smith"},{"key":"ref77","article-title":"Ensemble distribution distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Malinin"},{"key":"ref78","first-page":"719","article-title":"Generalized Bayesian posterior expectation distillation for deep neural networks","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Vadera"},{"key":"ref79","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019","journal-title":"arXiv:1912.02757"},{"key":"ref80","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref81","first-page":"6709","article-title":"Large scale structure of neural network loss landscapes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Fort"},{"key":"ref82","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","volume-title":"Bayesian Learning for Neural Networks","author":"Neal","year":"1996"},{"key":"ref83","first-page":"4712","article-title":"Dropout as a structured shrinkage prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nalisnick"},{"key":"ref84","article-title":"Using mode connectivity for loss landscape analysis","volume-title":"Proc. ICML Workshop Modern Trends Nonconvex Optim. Mach. Learn.","author":"Gotmare"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12502"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.2307\/2987588"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775151"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref89","first-page":"3792","article-title":"Verified uncertainty calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref90","first-page":"12316","article-title":"Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kull"},{"key":"ref91","first-page":"178","article-title":"Non-parametric calibration for classification","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Wenger"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"issue":"9","key":"ref93","first-page":"1","article-title":"Discriminative learning under covariate shift","volume":"10","author":"Bickel","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref94","first-page":"3219","article-title":"Calibrated prediction with covariate shift via unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Park"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1214\/20-aos2004"},{"key":"ref96","volume-title":"Reliable Machine Learning Via Distributional Robustness","author":"Namkoong","year":"2019"},{"key":"ref97","article-title":"Unsupervised calibration under covariate shift","author":"Pampari","year":"2020","journal-title":"arXiv:2006.16405"},{"key":"ref98","first-page":"19212","article-title":"Transferable calibration with lower bias and variance in domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00883"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.06.019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.018"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051581-6.50061-1"},{"key":"ref103","volume-title":"Finite-Dimensional Variational Inequalities Complementarity Problems","author":"Facchinei","year":"2007"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17508-4_9"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-55860-377-6.50048-7"},{"key":"ref106","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623758"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1131"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/183422.183423"},{"key":"ref110","first-page":"1","article-title":"SGM: Sequence generation model for multi-label classification","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Yang"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.10"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.370"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref114","article-title":"A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification","author":"Zhang","year":"2015","journal-title":"arXiv:1510.03820"},{"key":"ref115","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North American Chapter Assoc. Comput. Linguistics","author":"Devlin"},{"issue":"7","key":"ref116","first-page":"1","article-title":"Measuring calibration in deep learning","volume-title":"Proc. CVPR Workshops","volume":"2","author":"Nixon"},{"key":"ref117","first-page":"12236","article-title":"Calibration tests in multi-class classification: A unifying framework","volume-title":"Proc. 32th Int. Conf. Neural Inf. Process. Syst.","author":"Widmann"},{"key":"ref118","article-title":"Calibration tests beyond classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Widmann"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/0001-6918(70)90023-5"},{"key":"ref120","first-page":"2813","article-title":"A unified view of performance metrics: Translating threshold choice into expected classification loss","volume":"13","author":"Hernandez-Orallo","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_1"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"ref123","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1029"},{"key":"ref126","article-title":"A meta-analysis of the anomaly detection problem","author":"Emmott","year":"2015","journal-title":"arXiv:1503.01158"},{"key":"ref127","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref128","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17876-z"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2017"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00975"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba6f3"},{"issue":"1","key":"ref133","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The J. Mach. Learn. Res."},{"key":"ref134","first-page":"950","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Krogh"},{"key":"ref135","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref137","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref138","first-page":"10696","article-title":"Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Luo"},{"key":"ref139","article-title":"What are Bayesian neural network posteriors really like?","author":"Izmailov","year":"2021","journal-title":"arXiv:2104.14421"},{"key":"ref140","first-page":"10248","article-title":"How good is the Bayes posterior in deep neural networks really?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wenzel"},{"key":"ref141","article-title":"Isotropic SGD: A practical approach to Bayesian posterior sampling","author":"Franzese","year":"2020","journal-title":"arXiv:2006.05087"},{"key":"ref142","article-title":"All you need is a good functional prior for Bayesian deep learning","author":"Tran","year":"2020","journal-title":"arXiv:2011.12829"},{"key":"ref143","first-page":"202","article-title":"Avoiding pathologies in very deep networks","volume-title":"Proc. Artif. Intell. Statist.","author":"Duvenaud"},{"key":"ref144","article-title":"Uncertainty estimation with infinitesimal jackknife, its distribution and mean-field approximation","author":"Lu","year":"2020","journal-title":"arXiv:2006.07584"},{"key":"ref145","first-page":"14660","article-title":"Bayesian Layers: A module for neural network uncertainty","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Tran"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05929-w"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09761166.pdf?arnumber=9761166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T20:12:25Z","timestamp":1705954345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9761166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":146,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3168734","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}