{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:29:24Z","timestamp":1776680964585,"version":"3.51.2"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/iwqos.2018.8624183","type":"proceedings-article","created":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T22:26:02Z","timestamp":1551392762000},"page":"1-2","source":"Crossref","is-referenced-by-count":1132,"title":["Improved Adam Optimizer for Deep Neural Networks"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Zhang","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","author":"hu","year":"2017","journal-title":"Squeeze-and-Excitation Networks"},{"key":"ref10","author":"arpit","year":"2017","journal-title":"A closer look at memorization in deep networks"},{"key":"ref6","article-title":"Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref5","author":"zeiler","year":"2012","journal-title":"ADADELTA An Adaptive Learning Rate Method"},{"key":"ref12","author":"zagoruyko","year":"2016","journal-title":"Wide residual networks"},{"key":"ref8","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"ICLR 2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"}],"event":{"name":"2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS)","location":"Banff, AB, Canada","start":{"date-parts":[[2018,6,4]]},"end":{"date-parts":[[2018,6,6]]}},"container-title":["2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8613196\/8624116\/08624183.pdf?arnumber=8624183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T06:17:37Z","timestamp":1598249857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8624183\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/iwqos.2018.8624183","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}