{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T22:42:09Z","timestamp":1793400129226,"version":"4.5.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"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":["62176109"],"award-info":[{"award-number":["62176109"]}],"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":["62072429"],"award-info":[{"award-number":["62072429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["cstc2020jcyj-zdxmX0028"],"award-info":[{"award-number":["cstc2020jcyj-zdxmX0028"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"CAS \u201cLight of West China\u201d Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2020-009A"],"award-info":[{"award-number":["CAAIXSJLJJ-2020-009A"]}]},{"name":"Gansu Provincial Youth Doctoral Fund of Colleges and Universities","award":["2021QB-003"],"award-info":[{"award-number":["2021QB-003"]}]},{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"publisher","award":["20JR10RA639"],"award-info":[{"award-number":["20JR10RA639"]}],"id":[{"id":"10.13039\/501100004775","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":[[2023,4]]},"DOI":"10.1109\/tnnls.2021.3106044","type":"journal-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T20:02:18Z","timestamp":1630526538000},"page":"2156-2168","source":"Crossref","is-referenced-by-count":286,"title":["Activated Gradients for Deep Neural Networks"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0445-941X","authenticated-orcid":false,"given":"Mei","family":"Liu","sequence":"first","affiliation":[{"name":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangming","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohao","family":"Du","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Jin","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingsheng","family":"Shang","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738445"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028304"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2912781"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2964817"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2950853"},{"key":"ref8","article-title":"An overview of gradient descent optimization algorithms","volume-title":"arXiv:1609.04747","author":"Ruder","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2945012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2937496"},{"key":"ref13","first-page":"396","article-title":"Handwritten digit recognition with a backpropagation network","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"LeCun"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-020-00911-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.017"},{"key":"ref16","first-page":"435","article-title":"Preventing gradient explosions in gated recurrent units","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Kanai"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2778689"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.04.010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2998984"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2916892"},{"key":"ref21","first-page":"2933","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Yannand"},{"key":"ref22","first-page":"6389","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Li"},{"key":"ref23","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"arXiv:1609.04836","author":"Keskar","year":"2016"},{"key":"ref24","first-page":"5947","article-title":"Exploring generalization in deep learning","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Neyshabur"},{"key":"ref25","article-title":"SmoothOut: Smoothing out sharp minima to improve generalization in deep learning","volume-title":"arXiv:1805.07898","author":"Wen","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2018.03.013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/452"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2904921"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876179"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017202"},{"key":"ref33","article-title":"Gaussian error linear units (GELUs)","volume-title":"arXiv:1606.08415","author":"Hendrycks","year":"2016"},{"key":"ref34","article-title":"Searching for activation functions","volume-title":"arXiv:1710.05941","author":"Ramachandran","year":"2017"},{"key":"ref35","first-page":"1","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","volume-title":"Proc. IEEE Conf. Learn. Repr. (ICLR)","author":"Clevert"},{"key":"ref36","first-page":"971","article-title":"Self-normalizing neural networks","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Klambauer"},{"key":"ref37","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Veit"},{"key":"ref38","first-page":"1","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","volume-title":"Proc. IEEE Conf. Learn. Repr. (ICLR)","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857080"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2912082"},{"key":"ref41","first-page":"797","article-title":"Escaping from saddle points\u2014Online stochastic gradient for tensor decomposition","volume-title":"Proc. Conf. Learn. Theory (COLT)","author":"Ge"},{"key":"ref42","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Art. Intell. Statist. (AISTATS)","author":"Xavier"},{"key":"ref43","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. IEEE Conf. Learn. Repr. (ICLR)","author":"Kingma"},{"key":"ref44","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. IEEE Conf. Learn. Repr. (ICLR)","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref46","volume-title":"Advanced Engineering Mathematics","author":"O\u2019Neil","year":"2017"},{"key":"ref47","first-page":"1261","article-title":"A study of condition numbers for first-order optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Guille-Escuret"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01510-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref50","first-page":"630","article-title":"Identity mappings in deep residual networks","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Loshchilov"},{"key":"ref51","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. IEEE Conf. Learn. Repr. (ICLR)","author":"Loshchilov"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref53","first-page":"4470","article-title":"Dual path networks","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2872043"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1399"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10091960\/09526915.pdf?arnumber=9526915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:21:53Z","timestamp":1705015313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9526915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3106044","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}