{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:14:56Z","timestamp":1773058496310,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030014230","type":"print"},{"value":"9783030014247","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01424-7_55","type":"book-chapter","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T17:07:37Z","timestamp":1538413657000},"page":"564-573","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SPSA for Layer-Wise Training of Deep Networks"],"prefix":"10.1007","author":[{"given":"Benjamin","family":"Wulff","sequence":"first","affiliation":[]},{"given":"Jannis","family":"Schuecker","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Bauckhage","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,27]]},"reference":[{"key":"55_CR1","unstructured":"Baldi, P., Sadowski, P., Lu, Z.: Learning in the machine: random backpropagation and the deep learning channel. arXiv:1612.02734 [cs.LG] (2016)"},{"key":"55_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-642-03798-6_28","volume-title":"Pattern Recognition","author":"C Bauckhage","year":"2009","unstructured":"Bauckhage, C., Thurau, C.: Making archetypal analysis practical. In: Denzler, J., Notni, G., S\u00fc\u00dfe, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 272\u2013281. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-03798-6_28"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Lamblin, P., Popovic, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Proceedings NIPS (2006)","DOI":"10.7551\/mitpress\/7503.003.0024"},{"issue":"6","key":"55_CR4","first-page":"2006","volume":"17","author":"M Choy","year":"2006","unstructured":"Choy, M., Srinivasan, D., Cheu, R.: Neural networks for continuous online learning and control. IEEE Trans. Neural Netw. 17(6), 2006 (2006)","journal-title":"IEEE Trans. Neural Netw."},{"key":"55_CR5","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: Training deep neural networks with low precision multiplications. arXiv:1412.7024 [cs.LG] (2014)"},{"key":"55_CR6","unstructured":"Garipov, T., Izmailov, P., Podoprikhin, D., Vetrov, D., Wilson, A.: Loss surfaces, mode connectivity, and fast ensembling of DNNs. arXiv:1802.10026 [stat.ML] (2018)"},{"issue":"7","key":"55_CR7","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"Geoffrey E. Hinton","year":"2006","unstructured":"Hinton, G., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. In: Proceedings NIPS (2006)","journal-title":"Neural Computation"},{"issue":"1","key":"55_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Flat minima. Neural Comput. 9(1), 1\u201342 (1997)","journal-title":"Neural Comput."},{"issue":"2","key":"55_CR9","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1145\/321062.321069","volume":"8","author":"R Hooke","year":"1961","unstructured":"Hooke, R., Jeeves, T.: Direct search solution of numerical and statistical problems. J. ACM 8(2), 212\u2013229 (1961)","journal-title":"J. ACM"},{"key":"55_CR10","unstructured":"Izmailov, P., Garipov, D.P.T., Vetrov, D., Wilson, A.: Averaging weights leads to wider optima and better generalization. arXiv:1803.05407 [cs.LG] (2018)"},{"key":"55_CR11","unstructured":"Jaderberg, M., et al.: Decoupled neural interfaces using synthetic gradients. arXiv:1608.05343 [cs.LG] (2016)"},{"issue":"3","key":"55_CR12","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1214\/aoms\/1177729392","volume":"23","author":"J Kiefer","year":"1952","unstructured":"Kiefer, J., Wolfowitz, J.: Estimation of the maximum of a regression function. Ann. Math. Stat. 23(3), 462\u2013466 (1952)","journal-title":"Ann. Math. Stat."},{"key":"55_CR13","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"55_CR14","doi-asserted-by":"publisher","first-page":"13276","DOI":"10.1038\/ncomms13276","volume":"7","author":"Timothy P. Lillicrap","year":"2016","unstructured":"Lillicrap, T., Cownden, D., Tweed, D., Akerman, J.: Random synaptic feedback weights support error backpropagation for deep learning. Nat. Commun. 7(13276) (2016)","journal-title":"Nature Communications"},{"key":"55_CR15","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: Proceedings ICLR (2017)"},{"issue":"4","key":"55_CR16","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1093\/comjnl\/7.4.308","volume":"7","author":"J Nelder","year":"1965","unstructured":"Nelder, J., Mead, R.: A simplex method for function minimization. Comput. J. 7(4), 308\u2013313 (1965)","journal-title":"Comput. J."},{"issue":"3","key":"55_CR17","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22(3), 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Rosenfeld, A., Tsotsos, J.: Intriguing properties of randomly weighted networks: generalizing while learning next to nothing. arXiv:1802.00844 [cs.LG] (2018)","DOI":"10.1109\/CRV.2019.00010"},{"issue":"6088","key":"55_CR19","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D Rummelhart","year":"1986","unstructured":"Rummelhart, D., Hinton, G., Williams, R.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","journal-title":"Nature"},{"key":"55_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-540-87536-9_40","volume-title":"Artificial Neural Networks - ICANN 2008","author":"F Sehnke","year":"2008","unstructured":"Sehnke, F., Osendorfer, C., R\u00fcckstie\u00df, T., Graves, A., Peters, J., Schmidhuber, J.: Policy gradients with parameter-based exploration for control. In: K\u016frkov\u00e1, V., Neruda, R., Koutn\u00edk, J. (eds.) ICANN 2008. LNCS, vol. 5163, pp. 387\u2013396. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87536-9_40"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Smith, L.: Cyclical learning rates for training neural networks. In: Proceedings Winter Conference on Applications of Computer Vision. IEEE (2017)","DOI":"10.1109\/WACV.2017.58"},{"issue":"5","key":"55_CR22","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1109\/TNN.2007.912315","volume":"19","author":"Q Song","year":"2008","unstructured":"Song, Q., Spall, J., Soh, Y.C., Nie, J.: Robust neural network tracking controller using simultaneous perturbation stochastic approximation. IEEE Trans. Neural Netw. 19(5), 817\u2013835 (2008)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"3","key":"55_CR23","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/9.119632","volume":"37","author":"J Spall","year":"1992","unstructured":"Spall, J.: Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Autom. Control 37(3), 332\u2013341 (1992)","journal-title":"IEEE Trans. Autom. Control"},{"key":"55_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138","volume-title":"Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control","author":"J Spall","year":"2003","unstructured":"Spall, J.: Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control. Wiley, Hoboken (2003)"},{"key":"55_CR25","unstructured":"Taylor, G., Burmeister, R., Xu, Z., Singh, B., Patel, A., Goldstein, T.: Training neural networks without gradients: a scalable ADMM approach. In: Proceedings ICML (2016)"},{"issue":"2","key":"55_CR26","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10115-010-0352-6","volume":"29","author":"C Thurau","year":"2011","unstructured":"Thurau, C., Kersting, K., Wahabzada, M., Bauckhage, C.: Convex non-negative matrix factorization for massive datasets. Knowl. Inf. Syst. 29(2), 457\u2013478 (2011)","journal-title":"Knowl. Inf. Syst."},{"key":"55_CR27","unstructured":"Vande Wouver, A., Renotte, C., Remy, M.: On the use of simultaneuous perturbation stochastic approximation for neural network training. In: Proceedings American Control Conference. IEEE (1999)"},{"issue":"3\u20134","key":"55_CR28","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"R Williams","year":"1992","unstructured":"Williams, R.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01424-7_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:31:32Z","timestamp":1773048692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01424-7_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030014230","9783030014247"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01424-7_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"27 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rhodes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"360","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"139","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In addition there are 41 full poster papers and 11 short poster papers included in the proceedings","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}