{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:02:23Z","timestamp":1773586943727,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82172033"],"award-info":[{"award-number":["82172033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2031"],"award-info":[{"award-number":["U19B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971369"],"award-info":[{"award-number":["61971369"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52105126"],"award-info":[{"award-number":["52105126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017357","name":"Science and Technology Key Project of Fujian Province","doi-asserted-by":"publisher","award":["2019HZ020009"],"award-info":[{"award-number":["2019HZ020009"]}],"id":[{"id":"10.13039\/100017357","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tnnls.2022.3155181","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T20:56:27Z","timestamp":1647291387000},"page":"9029-9039","source":"Crossref","is-referenced-by-count":9,"title":["Learning Rate Dropout"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2334-4987","authenticated-orcid":false,"given":"Huangxing","family":"Lin","sequence":"first","affiliation":[{"name":"School of Informatics and National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China"}]},{"given":"Weihong","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3176-3217","authenticated-orcid":false,"given":"Yihong","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-5287","authenticated-orcid":false,"given":"Xinghao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Informatics, National Institute for Data Science in Health and Medicine, and Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-9400","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Informatics and Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}]},{"given":"John","family":"Paisley","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Data Science Institute, Columbia University, New York, NY, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref12","first-page":"118","article-title":"Fast dropout training","author":"wang","year":"2013","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref15","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"robinds","year":"1951","journal-title":"Ann Math Statist"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"3059","article-title":"Noisy activation functions","author":"gulcehre","year":"2016","journal-title":"Proc ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref10","article-title":"Adding gradient noise improves learning for very deep networks","author":"neelakantan","year":"2015","journal-title":"arXiv 1511 06807"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref17","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"2019","journal-title":"Proc ICLR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref16","first-page":"1","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2017","journal-title":"Proc NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.3.643"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/452"},{"key":"ref24","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref26","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref20","first-page":"1","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proc ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.428"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref29","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref8","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref7","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.514"},{"key":"ref4","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref3","first-page":"1","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2018","journal-title":"Proc ICLR"},{"key":"ref6","first-page":"1","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref5","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2019","journal-title":"Proc ICLR"},{"key":"ref40","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc ECCV"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10299535\/09733412.pdf?arnumber=9733412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:26:55Z","timestamp":1700508415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9733412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3155181","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}