{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T04:49:41Z","timestamp":1693284581401},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Korean Government [Ministry of Education (MOE)]","doi-asserted-by":"publisher","award":["2022R1I1A3065378"],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2018R1A5A7059549","2020R1A2C1014037"],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korean Government","award":["2020-0-01373"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3300034","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:35:18Z","timestamp":1690824918000},"page":"80656-80679","source":"Crossref","is-referenced-by-count":0,"title":["Advanced First-Order Optimization Algorithm With Sophisticated Search Control for Convolutional Neural Networks"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-1044-3089","authenticated-orcid":false,"given":"Kyung Soo","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9042-0599","authenticated-orcid":false,"given":"Yong Suk","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hanyang University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3187185"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3239424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3226629"},{"key":"ref52","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Human Lang Technol (NAACL-HLT)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3265998"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206389"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-020-00865-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref51","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.107970"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref48","first-page":"21370","article-title":"On the distance between two neural networks and the stability of learning","volume":"33","author":"bernstein","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref47","first-page":"9815","article-title":"Adaptive methods for nonconvex optimization","volume":"31","author":"zaheer","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref42","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21124054"},{"key":"ref44","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref43","article-title":"On the convergence of Adam and beyond","author":"reddi","year":"2019","journal-title":"arXiv 1904 09237"},{"key":"ref49","article-title":"AngularGrad: A new optimization technique for angular convergence of convolutional neural networks","author":"roy","year":"2021","journal-title":"arXiv 2105 10190"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3137638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202241"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262649"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2989819"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-020-01069-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.065"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108013"},{"key":"ref35","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932733"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041755"},{"key":"ref36","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.156"},{"key":"ref33","first-page":"14262","article-title":"On translation invariance in CNNs: Convolutional layers can exploit absolute spatial location","author":"kayhan","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108785"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref39","first-page":"2574","article-title":"A survey on large-scale machine learning","volume":"34","author":"wang","year":"2022","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref38","article-title":"Embedding principle: A hierarchical structure of loss landscape of deep neural networks","author":"zhang","year":"2021","journal-title":"arXiv 2111 15527"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0009-2614(85)80574-1"},{"key":"ref26","first-page":"18795","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref25","first-page":"2715","article-title":"Comparison of optimization techniques based on gradient descent algorithm: A review","volume":"18","author":"haji","year":"2021","journal-title":"PalArch’s J Archaeol Egypt\/Egyptol"},{"key":"ref20","author":"hinton","year":"2012","journal-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref28","article-title":"SAdam: A variant of Adam for strongly convex functions","author":"wang","year":"2019","journal-title":"arXiv 1905 02957"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955777"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950779"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10197412.pdf?arnumber=10197412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:05:58Z","timestamp":1693245958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10197412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3300034","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}