{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:45:42Z","timestamp":1755999942002,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Institute for Health Research (NIHR) Oxford Biomedical Research Centre"},{"name":"InnoHK Project at the Hong Kong Centre for Cerebro-cardiovascular Health Engineering"},{"name":"EPSRC Healthcare Technologies Challenge Award","award":["EP\/N020774\/1"],"award-info":[{"award-number":["EP\/N020774\/1"]}]},{"name":"Engineering for Development Research Fellowship provided by the Royal Academy of Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tnnls.2022.3210297","type":"journal-article","created":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T19:29:06Z","timestamp":1665516546000},"page":"6478-6491","source":"Crossref","is-referenced-by-count":3,"title":["Incremental Trainable Parameter Selection in Deep Neural Networks"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7006-1947","authenticated-orcid":false,"given":"Anshul","family":"Thakur","sequence":"first","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8149-8151","authenticated-orcid":false,"given":"Vinayak","family":"Abrol","sequence":"additional","affiliation":[{"name":"Infosys Centre for Artificial Intelligence, IIT Delhi, New Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7870-7098","authenticated-orcid":false,"given":"Pulkit","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1552-5630","authenticated-orcid":false,"given":"Tingting","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-8555","authenticated-orcid":false,"given":"David A.","family":"Clifton","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K"}]}],"member":"263","reference":[{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/JBHI.2016.2636665"},{"volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Noh","article-title":"Regularizing deep neural networks by noise: Its interpretation and optimization","key":"ref3"},{"key":"ref4","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TPAMI.2017.2701831"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref7","article-title":"Regularization for deep learning: A taxonomy","author":"Kuka\u010dka","year":"2017","journal-title":"arXiv:1710.10686"},{"issue":"1","key":"ref8","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Kingma"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1609\/aaai.v33i01.33014065"},{"key":"ref11","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"Pereyra","year":"2017","journal-title":"arXiv:1701.06548"},{"key":"ref12","article-title":"Robust learning with Jacobian regularization","author":"Hoffman","year":"2019","journal-title":"arXiv:1908.02729"},{"key":"ref13","first-page":"232","article-title":"Degrees of freedom in deep neural networks","volume-title":"Proc. 32nd Conf. Uncertainty Artif. Intell.","author":"Gao"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Barrett","article-title":"Implicit gradient regularization","key":"ref14"},{"key":"ref15","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012","journal-title":"arXiv:1207.0580"},{"key":"ref16","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Gal"},{"key":"ref17","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1016\/j.neunet.2018.09.009"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TSMC.2017.2664143"},{"key":"ref20","first-page":"5049","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Berthelot","article-title":"Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TPAMI.2018.2858821"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/72.165600"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.4467\/20838476si.18.003.10408"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1162\/NECO_a_00928"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/TSP.2017.2708039"},{"key":"ref27","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017","journal-title":"arXiv:1707.09835"},{"key":"ref28","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/BigData50022.2020.9378171"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Frankle","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","key":"ref30"},{"key":"ref31","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref32","article-title":"How noise affects the Hessian spectrum in overparameterized neural networks","author":"Wei","year":"2019","journal-title":"arXiv:1910.00195"},{"key":"ref33","first-page":"2232","article-title":"An investigation into neural net optimization via Hessian eigenvalue density","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghorbani"},{"key":"ref34","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1162\/neco.1997.9.1.1"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Keskar","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","key":"ref36"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"year":"2009","author":"Krizhevsky","article-title":"Learning multiple layers of features from tiny images","key":"ref40"},{"key":"ref41","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1038\/sdata.2016.35"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1038\/s41597-019-0103-9"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/JBHI.2021.3134835"},{"key":"ref46","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref47","article-title":"On lazy training in differentiable programming","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Chizat"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10517792\/09916206.pdf?arnumber=9916206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:48:12Z","timestamp":1714762092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9916206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":47,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3210297","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}