{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:09:13Z","timestamp":1781712553228,"version":"3.54.5"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-026-04736-9","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T16:26:35Z","timestamp":1769099195000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Variational Bayesian Gaussian Mixture Last Layer of Convolutional Neural Network"],"prefix":"10.1007","volume":"7","author":[{"given":"Mostafa","family":"Bakhouya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalid","family":"Elghazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Ramchoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Hadda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tawfik","family":"Masrour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"key":"4736_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2019.106816","volume":"142","author":"Y Kwon","year":"2020","unstructured":"Kwon Y, Won J-H, Kim BJ, Paik MC. Uncertainty quantification using bayesian neural networks in classification: Application to biomedical image segmentation. Comput Stat Data Anal. 2020;142:106816.","journal-title":"Comput Stat Data Anal"},{"key":"4736_CR2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar M, Pourpanah F, Hussain S, Rezazadegan D, Liu L, Ghavamzadeh M, et al. A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information fusion. 2021;76:243\u201397.","journal-title":"Information fusion"},{"key":"4736_CR3","doi-asserted-by":"crossref","unstructured":"K\u00fcppers F, Kronenberger J, Schneider J, Haselhoff A. Bayesian confidence calibration for epistemic uncertainty modelling. In: 2021 IEEE intelligent vehicles symposium (IV). IEEE 2021; pp. 466\u2013472","DOI":"10.1109\/IV48863.2021.9575841"},{"key":"4736_CR4","doi-asserted-by":"crossref","unstructured":"Alqarafi A, Batool H, Abbas T, Janjua JI, Ramay SA, Ahmed M. Estimating uncertainty in deep learning methods and applications. In: 2024 international conference on computer and applications (ICCA), IEEE, 2024;pp. 1\u20136 .","DOI":"10.1109\/ICCA62237.2024.10928030"},{"key":"4736_CR5","unstructured":"Guo C, Pleiss G, Sun Y, Weinberger KQ. On calibration of modern neural networks. In: international Cconference on achine learning, PMLR, 2017; pp. 1321\u20131330"},{"key":"4736_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105213","volume":"142","author":"M Loey","year":"2022","unstructured":"Loey M, El-Sappagh S, Mirjalili S. Bayesian-based optimized deep learning model to detect covid-19 patients using chest x-ray image data. Comput Biol Med. 2022;142:105213.","journal-title":"Comput Biol Med"},{"key":"4736_CR7","doi-asserted-by":"publisher","first-page":"54805","DOI":"10.1109\/ACCESS.2022.3175195","volume":"10","author":"G Melotti","year":"2022","unstructured":"Melotti G, Premebida C, Bird J, Faria D, Goncalves N. Reducing overconfidence predictions in autonomous driving perception. IEEE Access. 2022;10:54805\u201321.","journal-title":"IEEE Access"},{"key":"4736_CR8","unstructured":"Ritter H, Botev A, Barber D. A scalable laplace approximation for neural networks. In: 6th international conference on learning representations, ICLR 2018-conference track proceedings, 2018;vol. 6. International conference on representation learning"},{"key":"4736_CR9","unstructured":"Maddox WJ, Izmailov P, Garipov T, Vetrov DP, Wilson AG. A simple baseline for bayesian uncertainty in deep learning. Advances in neural information processing systems 2019;32"},{"issue":"8","key":"4736_CR10","doi-asserted-by":"publisher","first-page":"2008","DOI":"10.1109\/TPAMI.2018.2889774","volume":"41","author":"C Zhang","year":"2018","unstructured":"Zhang C, B\u00fctepage J, Kjellstr\u00f6m H, Mandt S. Advances in variational inference. IEEE Trans Pattern Anal Mach Intell. 2018;41(8):2008\u201326.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"4736_CR11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MCI.2022.3155327","volume":"17","author":"LV Jospin","year":"2022","unstructured":"Jospin LV, Laga H, Boussaid F, Buntine W, Bennamoun M. Hands-on bayesian neural networks-a tutorial for deep learning users. IEEE Comput Intell Mag. 2022;17(2):29\u201348.","journal-title":"IEEE Comput Intell Mag"},{"key":"4736_CR12","first-page":"2695","volume":"35","author":"Z Deng","year":"2022","unstructured":"Deng Z, Zhou F, Zhu J. Accelerated linearized laplace approximation for bayesian deep learning. Adv Neural Inf Process Syst. 2022;35:2695\u2013708.","journal-title":"Adv Neural Inf Process Syst"},{"key":"4736_CR13","doi-asserted-by":"crossref","unstructured":"Neal RM. Bayesian learning for neural networks. PhD thesis, Citeseer 1995","DOI":"10.1007\/978-1-4612-0745-0"},{"issue":"3","key":"4736_CR14","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1214\/21-STS840","volume":"37","author":"T Papamarkou","year":"2022","unstructured":"Papamarkou T, Hinkle J, Young MT, Womble D. Challenges in markov chain monte carlo for bayesian neural networks. Stat Sci. 2022;37(3):425\u201342.","journal-title":"Stat Sci"},{"key":"4736_CR15","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D. Weight uncertainty in neural network. In: International conference on machine learning, PMLR, 2015; pp. 1613\u20131622"},{"key":"4736_CR16","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1007\/s00521-013-1445-4","volume":"23","author":"S Sun","year":"2013","unstructured":"Sun S. A review of deterministic approximate inference techniques for bayesian machine learning. Neural Comput Appl. 2013;23:2039\u201350.","journal-title":"Neural Comput Appl"},{"issue":"518","key":"4736_CR17","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","volume":"112","author":"DM Blei","year":"2017","unstructured":"Blei DM, Kucukelbir A, McAuliffe JD. Variational inference: A review for statisticians. J Am Stat Assoc. 2017;112(518):859\u201377.","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"4736_CR18","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback S, Leibler RA. On information and sufficiency. Ann Math Stat. 1951;22(1):79\u201386.","journal-title":"Ann Math Stat"},{"key":"4736_CR19","doi-asserted-by":"crossref","unstructured":"Bakhouya M, Ramchoun H, Hadda M, Masrour T. Implicitly adaptive optimal proposal in variational inference for Bayesian learning. Int J Data Sci Anal. 2024;1\u201316","DOI":"10.1007\/s41060-024-00580-3"},{"key":"4736_CR20","unstructured":"Harrison J, Willes J, Snoek J. Variational bayesian last layers. In: The twelfth international conference on learning representations"},{"key":"4736_CR21","unstructured":"Wei Y, Khardon R. Variational inference on the final-layer output of neural networks. arXiv preprint arXiv:2302.02420 2023"},{"key":"4736_CR22","doi-asserted-by":"publisher","first-page":"123149","DOI":"10.1109\/ACCESS.2023.3329685","volume":"11","author":"F Fiedler","year":"2023","unstructured":"Fiedler F, Lucia S. Improved uncertainty quantification for neural networks with bayesian last layer. IEEE Access. 2023;11:123149\u201360.","journal-title":"IEEE Access"},{"key":"4736_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104329","volume":"156","author":"L Paparusso","year":"2023","unstructured":"Paparusso L, Melzi S, Braghin F. Real-time forecasting of driver-vehicle dynamics on 3d roads: A deep-learning framework leveraging bayesian optimisation. Transportation research part C emerging technologies. 2023;156:104329.","journal-title":"Transportation research part C emerging technologies"},{"key":"4736_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114010","volume":"273","author":"M Iaiani","year":"2023","unstructured":"Iaiani M, Tugnoli A, Cozzani V, Reniers G, Yang M. A bayesian-network approach for assessing the probability of success of physical security attacks to offshore oil&gas facilities. Ocean Eng. 2023;273:114010.","journal-title":"Ocean Eng"},{"key":"4736_CR25","doi-asserted-by":"publisher","first-page":"50188","DOI":"10.1109\/ACCESS.2021.3068867","volume":"9","author":"S Sinha","year":"2021","unstructured":"Sinha S, Franciosa P, Ceglarek D. Building a scalable and interpretable bayesian deep learning framework for quality control of free form surfaces. IEEE Access. 2021;9:50188\u2013208.","journal-title":"IEEE Access"},{"issue":"2","key":"4736_CR26","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1111\/j.2517-6161.1993.tb01911.x","volume":"55","author":"M West","year":"1993","unstructured":"West M. Approximating posterior distributions by mixtures. J Roy Stat Soc: Ser B (Methodol). 1993;55(2):409\u201322.","journal-title":"J Roy Stat Soc: Ser B (Methodol)"},{"key":"4736_CR27","unstructured":"Bishop C, Lawrence N, Jaakkola T, Jordan M. Approximating posterior distributions in belief networks using mixtures. Advances in neural information processing systems 1997;10"},{"key":"4736_CR28","doi-asserted-by":"crossref","unstructured":"Reynolds D. Gaussian mixture models. Encyclopedia of Biometrics, 2009;659\u2013663","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"4736_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12065-023-00900-9","volume":"17","author":"B Mostafa","year":"2024","unstructured":"Mostafa B, Hassan R, Mohammed H, Tawfik M. Gaussian mixture models for training Bayesian convolutional neural networks. Evol Intell. 2024;17:1\u201322.","journal-title":"Evol Intell"},{"key":"4736_CR30","unstructured":"Kingma DP, Salimans T, Welling M. Variational dropout and the local reparameterization trick. Advances in neural information processing systems 2015;28"},{"issue":"4","key":"4736_CR31","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","volume":"12","author":"DP Kingma","year":"2019","unstructured":"Kingma DP, Welling M. An introduction to variational autoencoders. Found Trends Mach Learn. 2019;12(4):307\u201392.","journal-title":"Found Trends Mach Learn"},{"key":"4736_CR32","unstructured":"Morningstar W, Vikram S, Ham C, Gallagher A, Dillon J. Automatic differentiation variational inference with mixtures. In: International conference on artificial intelligence and statistics, PMLR, 2021;pp. 3250\u20133258"},{"key":"4736_CR33","doi-asserted-by":"publisher","first-page":"70547","DOI":"10.1109\/ACCESS.2024.3401234","volume":"12","author":"R Chandra","year":"2024","unstructured":"Chandra R, Simmons J. Bayesian neural networks via mcmc: a python-based tutorial. IEEE Access. 2024;12:70547.","journal-title":"IEEE Access"},{"key":"4736_CR34","doi-asserted-by":"crossref","unstructured":"Hinton GE, Van\u00a0Camp D. Keeping the neural networks simple by minimizing the description length of the weights. In: Proceedings of the sixth annual conference on computational learning theory, 1993;pp. 5\u201313","DOI":"10.1145\/168304.168306"},{"key":"4736_CR35","unstructured":"Barber D, Bishop C. Ensemble learning in bayesian neural networks. NATO ASI ser 1998;215\u2013237"},{"key":"4736_CR36","unstructured":"Graves A. Practical variational inference for neural networks. In: Proceedings of the 24th international conference on neural information processing systems, 2011;pp. 2348\u20132356"},{"key":"4736_CR37","unstructured":"Kingma DP. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 2013"},{"key":"4736_CR38","unstructured":"Gal Y, Ghahramani Z. Bayesian convolutional neural networks with bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158 2015"},{"key":"4736_CR39","unstructured":"Lakshminarayanan B, Pritzel A, Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems 2017;30"},{"key":"4736_CR40","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, et al. Recent advances in convolutional neural networks. Pattern Recogn. 2018;77:354\u201377.","journal-title":"Pattern Recogn"},{"key":"4736_CR41","unstructured":"Ranganath R, Gerrish S, Blei D. Black box variational inference. In: Artificial intelligence and statistics, PMLR, 2014; pp. 814\u2013822"},{"key":"4736_CR42","doi-asserted-by":"crossref","unstructured":"Hershey JR, Olsen PA. Approximating the Kullback Leibler divergence between gaussian mixture models. In: IEEE international conference on acoustics, speech, and signal processing 2007","DOI":"10.1109\/ICASSP.2007.366913"},{"issue":"1","key":"4736_CR43","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1214\/07-AOAS114","volume":"1","author":"DM Blei","year":"2007","unstructured":"Blei DM, Lafferty JD. A correlated topic model of science. The Annals of Applied Statistics. 2007;1(1):17\u201335.","journal-title":"The Annals of Applied Statistics"},{"key":"4736_CR44","volume-title":"MNIST handwritten digit database","author":"Y LeCun","year":"2010","unstructured":"LeCun Y, Cortes C, Burges C, et al. MNIST handwritten digit database. NJ, USA: Florham Park; 2010."},{"key":"4736_CR45","unstructured":"Xiao H, Rasul K, Vollgraf R. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 2017"},{"key":"4736_CR46","unstructured":"Alex K. Learning multiple layers of features from tiny images. https:\/\/www. cs. toronto. edu\/kriz\/learning-features-2009-TR. pdf 2009"},{"key":"4736_CR47","unstructured":"Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY. Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning, Granada, 2011;vol. 2011, pp. 4"},{"key":"4736_CR48","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016;pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"4736_CR49","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology. 1982;143(1):29\u201336.","journal-title":"Radiology"},{"key":"4736_CR50","unstructured":"Hendrycks D, Gimpel K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 2016"},{"key":"4736_CR51","unstructured":"Yan L, Dodier RH, Mozer M, Wolniewicz RH. Optimizing classifier performance via an approximation to the wilcoxon-mann-whitney statistic. In: Proceedings of the 20th international conference on machine learning (icml-03), 2003;pp. 848\u2013855"},{"issue":"4","key":"4736_CR52","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.orl.2020.05.012","volume":"48","author":"W Ma","year":"2020","unstructured":"Ma W, Lejeune MA. A distributionally robust area under curve maximization model. Oper Res Lett. 2020;48(4):460\u20136.","journal-title":"Oper Res Lett"},{"key":"4736_CR53","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s00180-015-0638-y","volume":"32","author":"N Depraetere","year":"2017","unstructured":"Depraetere N, Vandebroek M. A comparison of variational approximations for fast inference in mixed logit models. Comput Statistics. 2017;32:93\u2013125.","journal-title":"Comput Statistics"},{"key":"4736_CR54","unstructured":"Knowles D, Minka T. Non-conjugate variational message passing for multinomial and binary regression. Advances in neural information processing systems 2011;24"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04736-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-026-04736-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-04736-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T23:04:36Z","timestamp":1769209476000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-026-04736-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":54,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["4736"],"URL":"https:\/\/doi.org\/10.1007\/s42979-026-04736-9","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,22]]},"assertion":[{"value":"4 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"131"}}