{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:07:25Z","timestamp":1767092845386},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030243074"},{"type":"electronic","value":"9783030243081"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-24308-1_55","type":"book-chapter","created":{"date-parts":[[2019,6,28]],"date-time":"2019-06-28T11:03:03Z","timestamp":1561719783000},"page":"704-715","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Experimental Comparison of Stochastic Optimizers in Deep Learning"],"prefix":"10.1007","author":[{"given":"Emmanuel","family":"Okewu","sequence":"first","affiliation":[]},{"given":"Philip","family":"Adewole","sequence":"additional","affiliation":[]},{"given":"Oladipupo","family":"Sennaike","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,29]]},"reference":[{"key":"55_CR1","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. DIRO, Universit\u00e9 de Montr\u00e9al, Montr\u00e9al (2010)"},{"issue":"7553","key":"55_CR2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Yann LeCun","year":"2015","unstructured":"Bengio, Y., LeCun, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015). https:\/\/doi.org\/10.1038\/nature14539 . Bibcode:2015Natur.521..436L. PMID 26017442","journal-title":"Nature"},{"key":"55_CR3","unstructured":"Koushik, J., Hayashi, H.: Improving stochastic gradient descent with feedback. In: Conference Paper at ICLR 2017"},{"key":"55_CR4","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121\u20132159 (2011)"},{"key":"55_CR5","unstructured":"Kim, D., Fessler, J.A.: Optimized first-order methods for smooth convex minimization. Math. Prog. 151, 8\u2013107 (2016)"},{"key":"55_CR6","unstructured":"Walia, A.S.: Types of Optimization Algorithms used in Neural Networks and Ways to Optimize Gradient Descent (2017)"},{"key":"55_CR7","unstructured":"Shridhar, K.: A Beginners Guide to Deep Learning (2017)"},{"key":"55_CR8","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.neunet.2018.05.017","volume":"105","author":"Dat Thanh Tran","year":"2018","unstructured":"Tran, D.T., Iosifidis, A., Gabbouj, M.: Improving efficiency in convolutional neural networks with multilinear filters. Neural Netw. 105, 328\u2013339 (2018)","journal-title":"Neural Networks"},{"key":"55_CR9","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.cam.2017.07.008","volume":"329","author":"Ji Li","year":"2018","unstructured":"Li, J., Zhou, T., Wang, C.: On global convergence of gradient descent algorithms for generalized phase retrieval problem. J. Comput. Appl. Math. 329, 202\u2013222 (2018)","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"55_CR10","unstructured":"Anandkumar, A.: Nonconvex optimization: challenges and recent successes. In: ICML 2016 Tutorial"},{"key":"55_CR11","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Published as a Conference Paper at ICLR 2015"},{"key":"55_CR12","unstructured":"Brownlee, J.: How to setup a python environment for machine learning and deep learning with anaconda. In: Python Machine Learning (2017)"},{"key":"55_CR13","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.neucom.2017.06.058","volume":"272","author":"Guoqi Li","year":"2018","unstructured":"Li, G., et al.: Training deep neural networks with discrete state transition. Neurocomputing 272, 154\u2013162 (2018)","journal-title":"Neurocomputing"},{"key":"55_CR14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J\u00fcrgen Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015). arXiv:1404.7828 \u202f. https:\/\/doi.org\/10.1016\/j.neunet.2014.09.003 . PMID 25462637","journal-title":"Neural Networks"},{"key":"55_CR15","unstructured":"Sutskever, I.: Training recurrent neural networks (PDF). Ph.D., University of Toronto, p. 74 (2013)"},{"key":"55_CR16","doi-asserted-by":"crossref","unstructured":"Mei, S.: A mean field view of the landscape of two-layer neural networks. In: Proceedings of the National Academy of Sciences (2018)","DOI":"10.1073\/pnas.1806579115"},{"key":"55_CR17","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: For developing SGD in their 1951 article titled \u201cA Stochastic Approximation Method\u201d (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"55_CR18","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.E.: On the importance of initialization and momentum in deep learning\u2019(PDF). In: Dasgupta, S., Mcallester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning (ICML-13), Atlanta, GA, vol. 28, pp. 1139\u20131147. Accessed 14 Jan 2016"},{"issue":"6088","key":"55_CR19","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","journal-title":"Nature"},{"key":"55_CR20","unstructured":"Nesterov (1983)"},{"key":"55_CR21","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"55_CR22","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)"},{"key":"55_CR23","unstructured":"Graves, A.: Generating Sequences with Recurrent Neural Networks (2014)"},{"key":"55_CR24","unstructured":"Yal\u00e7\u0131n, O.G.: Image Classification in 10 Minutes with MNIST\u00a0Dataset (2018)"},{"key":"55_CR25","unstructured":"Torres, J.: Convolutional Neural Networks for Beginners. Practical Guide with Python and Keras (2018)"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-24308-1_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,8]],"date-time":"2021-01-08T11:45:47Z","timestamp":1610106347000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-24308-1_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030243074","9783030243081"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-24308-1_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Saint Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}