{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T21:05:33Z","timestamp":1780434333172,"version":"3.54.1"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tai.2025.3644334","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:50:34Z","timestamp":1765997434000},"page":"3068-3082","source":"Crossref","is-referenced-by-count":0,"title":["Regularization in Neural Networks: A Survey and Empirical Analysis of Approaches"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0335-136X","authenticated-orcid":false,"given":"Christiaan P.","family":"Opperman","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Pretoria, Pretoria, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3546-1467","authenticated-orcid":false,"given":"Anna S.","family":"Bosman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Pretoria, Pretoria, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-2632","authenticated-orcid":false,"given":"Katherine M.","family":"Malan","sequence":"additional","affiliation":[{"name":"Department of Decision Sciences, University of South Africa, Tshwane, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref3","first-page":"87","article-title":"Understanding generalization through visualizations","volume-title":"Proc. I Can\u2019t Believe It\u2019s Not Better! at NeurIPS Workshops","volume":"137","author":"Huang","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/9781009025096.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref6","first-page":"129","article-title":"What is the state of neural network pruning?","volume":"2","author":"Blalock","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref7","article-title":"Regularization for deep learning: A taxonomy","author":"Kuka\u010dka","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09784-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3510413"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/UBMK.2019.8907003"},{"key":"ref13","article-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"ref14","article-title":"A survey on mixup augmentations and beyond","author":"Jin","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-019-04094-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"ref17","article-title":"Effective data augmentation with diffusion models","author":"Trabucco","year":"2023"},{"key":"ref18","article-title":"Dataset augmentation in feature space","author":"DeVries","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10004-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109347"},{"key":"ref23","article-title":"Image data augmentation for deep learning: A survey","author":"Yang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.3.643"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/72.105415"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628917"},{"key":"ref28","article-title":"Rethinking the inception architecture for computer vision","author":"Christian","year":"2015"},{"key":"ref29","first-page":"6448","article-title":"Does label smoothing mitigate label noise","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Lukasik","year":"Jul. 13\u201318, 2020"},{"key":"ref30","article-title":"When does label smoothing help","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rafael","year":"2019"},{"key":"ref31","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"Pereyra","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2005.1532889"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3335841"},{"key":"ref34","volume-title":"Deep Learning.","author":"Goodfellow","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113196"},{"key":"ref36","first-page":"7594","article-title":"Toward understanding the importance of noise in training neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2019"},{"issue":"3","key":"ref37","first-page":"1","article-title":"To transfer or not to transfer","volume":"898","author":"Rosenstein","year":"2005","journal-title":"Proc. NIPS Workshop Transfer Learn."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref39","article-title":"A recent survey of heterogeneous transfer learning","author":"Runxue","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0080"},{"key":"ref41","first-page":"20852","article-title":"The generalization-stability trade-off in neural network pruning","volume":"33","author":"Bartoldson","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2750"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129382"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8052-6_112"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"ref46","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref47","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. ICLR","author":"Lee","year":"2019"},{"key":"ref48","first-page":"9356","article-title":"DropNet: Reducing neural network complexity via iterative pruning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Tan","year":"Jul. 13\u201318, 2020"},{"key":"ref49","first-page":"1","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. ICLR","author":"Li","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103511"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref52","first-page":"381","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","volume":"13","author":"Caruana","year":"2000","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/20M1336072"},{"key":"ref55","first-page":"153","article-title":"The difficulty of training deep architectures and the effect of unsupervised pre-training","volume-title":"Proc. Artif. Intell. Statist.","author":"Erhan","year":"2009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-017-0968-2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00112"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3506283"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref61","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3187013"},{"key":"ref63","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume":"2","author":"Morgan","year":"1989","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.11.035"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00010-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2009.5178626"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.915114"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2000.876636"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3250241"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853582"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11768"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.305"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11624"},{"key":"ref75","article-title":"Comparison of batch normalization and weight normalization algorithms for the large-scale image classification","author":"Gitman","year":"2017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.102929"},{"key":"ref78","first-page":"4119","article-title":"Supervised representation learning: Transfer learning with deep autoencoders","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Zhuang","year":"2015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref80","first-page":"7002","article-title":"Loss function learning for domain generalization by implicit gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao","year":"2022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-436"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.113"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93314-2_11"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185777"},{"key":"ref85","first-page":"529","article-title":"Simplifying neural nets by discovering flat minima","volume":"7","author":"Hochreiter","year":"1994","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23783-6_41"},{"key":"ref87","article-title":"Low-pass filtering SGD for recovering flat optima in the deep learning optimization landscape","author":"Bisla","year":"2022"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206727"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab39d9"},{"key":"ref90","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017"},{"key":"ref91","first-page":"18420","article-title":"Relative flatness and generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Petzka","year":"2021"},{"key":"ref92","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2019"},{"key":"ref93","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2021"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1206"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.l803.03635"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref97","article-title":"Learning sparse networks using targeted dropout","author":"Gomez","year":"2019"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01604"},{"key":"ref100","article-title":"Diabetes","author":"Kahn"},{"key":"ref101","article-title":"Cirrhosis patient survival prediction","author":"Dickson","year":"1989"},{"key":"ref102","article-title":"Magic gamma telescope","author":"Bock","year":"2004"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-017-0154-4"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2009.05.016"},{"key":"ref105","article-title":"30 types of balls updated image classification","author":"Piosenka","year":"2023"},{"key":"ref106","article-title":"Bean leaf lesions classification","year":"2023"},{"key":"ref107","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref108","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref109","article-title":"Nike, Adidas and Converse shoes images","year":"2022"},{"key":"ref110","article-title":"Pyhopper\u2014Hyperparameter optimization","author":"Mathias","year":"2022"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11541276\/11301782.pdf?arnumber=11301782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:09:53Z","timestamp":1780430993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11301782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":110,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3644334","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}