{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:30:09Z","timestamp":1782394209274,"version":"3.54.5"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107400"],"award-info":[{"award-number":["2020AAA0107400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LR19F020004"],"award-info":[{"award-number":["LR19F020004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20222"],"award-info":[{"award-number":["U20A20222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"OPPO Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tnnls.2022.3174207","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T20:33:30Z","timestamp":1653338010000},"page":"326-337","source":"Crossref","is-referenced-by-count":5,"title":["Epoch-Evolving Gaussian Process Guided Learning for Classification"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3083-1035","authenticated-orcid":false,"given":"Jiabao","family":"Cui","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-4534","authenticated-orcid":false,"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5242-138X","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-1116","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511569920.003"},{"key":"ref2","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. ICML","author":"Sutskever"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref4","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"ref5","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48229-6_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/biom.12875"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref10","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"arXiv:1606.04080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","first-page":"1","article-title":"Memory-based parameter adaptation","volume-title":"Proc. ICLR","author":"Sprechmann"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00069"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.76"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957109"},{"key":"ref23","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. NeurIPS","author":"Lopez-Paz"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953622"},{"key":"ref26","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. NeurIPS","author":"Shin"},{"key":"ref27","article-title":"Generative replay with feedback connections as a general strategy for continual learning","author":"van de Ven","year":"2018","journal-title":"arXiv:1809.10635"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927369"},{"key":"ref30","first-page":"1","article-title":"Variational continual learning","volume-title":"Proc. ICLR","author":"Nguyen"},{"key":"ref31","first-page":"350","article-title":"Experience replay for continual learning","volume-title":"Proc. NeurIPS","author":"Rolnick"},{"key":"ref32","first-page":"1","article-title":"Continual learning with Bayesian neural networks for non-stationary data","volume-title":"Proc. ICLR","author":"Kurle"},{"key":"ref33","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","author":"Goodfellow"},{"key":"ref34","first-page":"1","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. ICLR","author":"Keskar"},{"key":"ref35","first-page":"1","article-title":"Don\u2019t decay the learning rate, increase the batch size","volume-title":"Proc. ICLR","author":"Smith"},{"key":"ref36","first-page":"1","article-title":"An exponential learning rate schedule for deep learning","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref37","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref38","article-title":"Gradient-based hyperparameter optimization over long horizons","author":"Micaelli","year":"2020","journal-title":"arXiv:2007.07869"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979121"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955777"},{"key":"ref41","first-page":"1","article-title":"Neumann optimizer: A practical optimization algorithm for deep neural networks","volume-title":"Proc. ICLR","author":"Krishnan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00889"},{"key":"ref43","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. ICLR","author":"Luo"},{"key":"ref44","article-title":"When does label smoothing help?","author":"M\u00fcller","year":"2019","journal-title":"arXiv:1906.02629"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2162429"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2906302"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979745"},{"key":"ref49","first-page":"207","article-title":"Deep Gaussian processes","volume-title":"Proc. Artif. Intell. Med. Stat.","author":"Damianou"},{"key":"ref50","first-page":"1472","article-title":"Deep Gaussian processes for regression using approximate expectation propagation","volume-title":"Proc. ICML","author":"Bui"},{"key":"ref51","first-page":"370","article-title":"Deep kernel learning","volume-title":"Proc. Artif. Intell. Med. Stat.","author":"Wilson"},{"key":"ref52","first-page":"2586","article-title":"Stochastic variational deep kernel learning","volume-title":"Proc. NeurIPS","volume":"29","author":"Wilson"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.11.002"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00540"},{"key":"ref55","first-page":"1","article-title":"Conditional neural processes","volume-title":"Proc. ICML","author":"Garnelo"},{"issue":"1","key":"ref56","first-page":"3649","article-title":"A unifying framework for Gaussian process pseudo-point approximations using power expectation propagation","volume":"18","author":"Bui","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","first-page":"14648","article-title":"Exact Gaussian processes on a million data points","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1194909"},{"key":"ref59","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"18","author":"Snelson"},{"key":"ref60","first-page":"333","article-title":"A framework for evaluating approximation methods for Gaussian process regression","volume":"14","author":"Chalupka","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2272403"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2316530"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042525"},{"key":"ref64","article-title":"The variational Gaussian process","author":"Tran","year":"2015","journal-title":"arXiv:1511.06499"},{"key":"ref65","first-page":"10369","article-title":"Gaussian process prior variational autoencoders","volume-title":"Proc. NeurIPS","author":"Casale"},{"key":"ref66","first-page":"1690","article-title":"Bayesian semi-supervised learning with graph Gaussian processes","volume-title":"Proc. NeurIPS","volume":"31","author":"Ng"},{"key":"ref67","first-page":"3227","article-title":"Robust process regression with a student-t likelihood","volume":"12","author":"Jyl\u00e4nki","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref68","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv:1503.02531"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/34.955109"},{"key":"ref71","first-page":"2377","article-title":"Training very deep networks","volume-title":"Proc. NeurIPS","author":"Srivastava"},{"key":"ref72","first-page":"1","article-title":"Fix your classifier: The marginal value of training the last weight layer","volume-title":"Proc. ICLR","author":"Elad"},{"key":"ref73","first-page":"1","article-title":"Complement objective training","volume-title":"Proc. ICLR","author":"Hao-Yun"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","article-title":"Switchable precision neural networks","author":"Guerra","year":"2020","journal-title":"arXiv:2002.02815"},{"key":"ref76","article-title":"Improving generalization performance by switching from Adam to SGD","author":"Keskar","year":"2017","journal-title":"arXiv:1712.07628"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09779793.pdf?arnumber=9779793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:31:55Z","timestamp":1705026715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9779793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":76,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3174207","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}