{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:19:20Z","timestamp":1773825560933,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Appl. Math."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s40314-023-02307-9","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T04:01:32Z","timestamp":1682913692000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9947-1408","authenticated-orcid":false,"given":"A.","family":"El Mouatasim","sequence":"first","affiliation":[]},{"given":"J. E. Souza","family":"de Cursi","sequence":"additional","affiliation":[]},{"given":"R.","family":"Ellaia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,1]]},"reference":[{"key":"2307_CR1","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/s10957-012-0167-6","volume":"157","author":"AM Bagirov","year":"2013","unstructured":"Bagirov AM, Jin L, Karmitsa N, Al Nuaimat A, Sultanova N (2013) Subgradient method for nonconvex nonsmooth optimization. J Optim Theory Appl 157:416\u2013435","journal-title":"J Optim Theory Appl"},{"issue":"1","key":"2307_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1\u2013127","journal-title":"Found Trends Mach Learn"},{"key":"2307_CR3","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"C Bishop","year":"1995","unstructured":"Bishop C (1995) Neural networks for pattern recognition. Clarendon Press, Oxford"},{"key":"2307_CR4","volume-title":"Pattern recognition and machine learning","author":"C Bishop","year":"2006","unstructured":"Bishop C (2006) Pattern recognition and machine learning. Springer, New York"},{"key":"2307_CR5","unstructured":"Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang J et al (2016) End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316"},{"key":"2307_CR6","doi-asserted-by":"crossref","unstructured":"Botev A, Lever G, Barber D (2017) Nesterov\u2019s accelerated gradient and momentum as approximations to regularised update descent. In: Neural networks (IJCNN) 2017 international joint conference on, pp 1899\u20131903","DOI":"10.1109\/IJCNN.2017.7966082"},{"key":"2307_CR7","doi-asserted-by":"crossref","unstructured":"Ciresan DC, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. Comput Res Repos. arXiv:abs\/1202.2745","DOI":"10.1109\/CVPR.2012.6248110"},{"issue":"2","key":"2307_CR8","doi-asserted-by":"publisher","first-page":"1693","DOI":"10.1137\/18M1231559","volume":"30","author":"Y Cui","year":"2020","unstructured":"Cui Y, He Z, Pang J (2020) Multicomposite nonconvex optimization for training deep neural networks. SIAM J Optim 30(2):1693\u20131723","journal-title":"SIAM J Optim"},{"key":"2307_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12603-5","volume-title":"Nondifferentiable optimization","author":"VF Dem\u2019vanov","year":"1985","unstructured":"Dem\u2019vanov VF, Vasil\u2019ev LV (1985) Nondifferentiable optimization. Optimization Software, Inc., Publications Division, New York"},{"key":"2307_CR10","first-page":"2121","volume":"12","author":"JC Duchi","year":"2011","unstructured":"Duchi JC, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121\u20132159","journal-title":"J Mach Learn Res"},{"key":"2307_CR11","volume-title":"Pattern classification","author":"R Duda","year":"2001","unstructured":"Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, New York"},{"key":"2307_CR12","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11760-020-01746-9","volume":"15","author":"I El Jaafari","year":"2021","unstructured":"El Jaafari I, Ellahyani A, Charfi S (2021) Parametric rectified nonlinear unit (PRenu) for convolution neural networks. J Signal Image Video Process (SIViP) 15:241\u2013246","journal-title":"J Signal Image Video Process (SIViP)"},{"issue":"1","key":"2307_CR13","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11075-017-0366-1","volume":"78","author":"A El Mouatasim","year":"2018","unstructured":"El Mouatasim A (2018) Implementation of reduced gradient with bisection algorithms for non-convex optimization problem via stochastic perturbation. J Numer Algorithms 78(1):41\u201362","journal-title":"J Numer Algorithms"},{"issue":"6","key":"2307_CR14","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1007\/s11760-019-01453-0","volume":"13","author":"A El Mouatasim","year":"2019","unstructured":"El Mouatasim A (2019) Control proximal gradient algorithm for $$\\ell _1$$ regularization image. J Signal Image Video Process (SIViP) 13(6):1113\u20131121","journal-title":"J Signal Image Video Process (SIViP)"},{"key":"2307_CR15","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1007\/s11760-020-01696-2","volume":"14","author":"A El Mouatasim","year":"2020","unstructured":"El Mouatasim A (2020) Fast gradient descent algorithm for image classification with neural networks. J Signal Image Video Process (SIViP) 14:1565\u20131572","journal-title":"J Signal Image Video Process (SIViP)"},{"key":"2307_CR16","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s11760-015-0815-z","volume":"9","author":"A El Mouatasim","year":"2015","unstructured":"El Mouatasim A, Wakrim M (2015) Control subgradient algorithm for image regularization. J Signal Image Video Process (SIViP) 9:275\u2013283","journal-title":"J Signal Image Video Process (SIViP)"},{"issue":"4","key":"2307_CR17","first-page":"463","volume":"16","author":"A El Mouatasim","year":"2006","unstructured":"El Mouatasim A, Ellaia R, Souza de Cursi JE (2006) Random perturbation of variable metric method for unconstraint nonsmooth nonconvex optimization. Appl Math Comput Sci 16(4):463\u2013474","journal-title":"Appl Math Comput Sci"},{"issue":"2","key":"2307_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.2478\/v10006-011-0024-z","volume":"21","author":"A El Mouatasim","year":"2011","unstructured":"El Mouatasim A, Ellaia R, Souza de Cursi JE (2011) Projected variable metric method for linear constrained nonsmooth global optimization via perturbation stochastic. Int J Appl Math Comput Sci 21(2):317\u2013329","journal-title":"Int J Appl Math Comput Sci"},{"key":"2307_CR19","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.amc.2013.10.024","volume":"226","author":"A El Mouatasim","year":"2014","unstructured":"El Mouatasim A, Ellaia R, Souza de Cursi JE (2014) Stochastic perturbation of reduced gradient & GRG methods for nonconvex programming problems. J Appl Math Comput 226:198\u2013211","journal-title":"J Appl Math Comput"},{"key":"2307_CR20","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1237\/2\/022030","author":"J Feng","year":"2019","unstructured":"Feng J, Lu S (2019) Performance analysis of various activation functions in artificial neural networks. J Phys Conf Ser. https:\/\/doi.org\/10.1088\/1742-6596\/1237\/2\/022030","journal-title":"J Phys Conf Ser"},{"key":"2307_CR21","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: International conference on artificial intelligence and statistics, pp 249\u2013256"},{"key":"2307_CR22","volume-title":"Neural networks a comprehensive foundation","author":"S Haykin","year":"2005","unstructured":"Haykin S (2005) Neural networks a comprehensive foundation. Pearson Education, New Delhi"},{"key":"2307_CR23","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov R (2012) Improving neural networks by preventing co-adaptation of feature detectors. Comput Res Repos. arXiv:abs\/1207.0580"},{"key":"2307_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-06073-2","volume-title":"Deep learning: fundamentals, theory and applications","author":"K Huang","year":"2019","unstructured":"Huang K, Hussain A, Wang Q, Zhang R (2019) Deep learning: fundamentals, theory and applications. Springer, Berlin"},{"key":"2307_CR25","doi-asserted-by":"crossref","unstructured":"Jarrett K, Kavukcuogl K, Ranzato M, LeCun Y (2009) What is the best multi-stage architecture for object recognition? In: International conference on computer vision, pp 2146\u20132153","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"2307_CR26","unstructured":"Josef S (2022) A few samples from the MNIST test dataset. https:\/\/commons.wikimedia.org\/wiki\/File:MnistExamples.png. Accessed 12 Dec. Under Creative Commons Attribution-ShareAlike 4.0 International License"},{"key":"2307_CR27","doi-asserted-by":"publisher","unstructured":"Khalij L, de Cursi ES (2021) Uncertainty quantification in data fitting neural and Hilbert networks. In: Proceedings of the 5th international symposium on uncertainty quantification and stochastic modelling, pp 222\u2013241. https:\/\/doi.org\/10.1007\/978-3-030-53669-5_17","DOI":"10.1007\/978-3-030-53669-5_17"},{"key":"2307_CR28","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations, San Diego, CA"},{"key":"2307_CR29","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neunet.2018.11.005","volume":"110","author":"E Konstantin","year":"2019","unstructured":"Konstantin E, Johannes S (2019) A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural Netw 110:232\u2013242","journal-title":"Neural Netw"},{"key":"2307_CR30","first-page":"1097","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 60:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"2307_CR31","unstructured":"Kutyniok G (2022) The mathematics of artificial intelligence. arXiv preprint arXiv:2203.08890"},{"key":"2307_CR32","first-page":"143","volume":"19","author":"Y LeCun","year":"1989","unstructured":"LeCun Y (1989) Generalization and network design strategies. Connect Perspect 19:143\u2013155","journal-title":"Connect Perspect"},{"key":"2307_CR33","unstructured":"LeCun Y, Cortes C (2010) MNIST handwritten digit database"},{"issue":"4","key":"2307_CR34","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551","journal-title":"Neural Comput"},{"key":"2307_CR35","doi-asserted-by":"crossref","unstructured":"LeCun Y, Kavukvuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: International symposium on circuits and systems, vol 5, pp 253\u2013256","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"2307_CR36","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1007\/s10957-019-01475-1","volume":"181","author":"Z Liu","year":"2019","unstructured":"Liu Z, Liu H (2019) An efficient gradient method with approximately optimal stepsize based on tensor model for unconstrained optimization. J Optim Theory Appl 181:608\u2013633","journal-title":"J Optim Theory Appl"},{"key":"2307_CR37","doi-asserted-by":"crossref","unstructured":"Li J, Yang X (2020) A cyclical learning rate method in deep learning training. In: International conference on computer, information and telecommunication systems (CITS), pp 1\u20135","DOI":"10.1109\/CITS49457.2020.9232482"},{"key":"2307_CR38","unstructured":"Minsky ML (1954) Theory of neural-analog reinforcement systems and its application to the brain-model problem. Ph.D. dissertation, Princeton University"},{"key":"2307_CR39","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.3390\/electronics10162029","volume":"10","author":"K Nakamura","year":"2021","unstructured":"Nakamura K, Derbel B, Won K-J, Hong B-W (2021) Learning-rate annealing methods for deep neural networks. Electronics 10:2029","journal-title":"Electronics"},{"key":"2307_CR40","unstructured":"Neutelings I (2022) Graphics with TikZ in LaTeX. Neural networks. https:\/\/tikz.net\/neura_networks. Accessed 12 Dec. Under Creative Commons Attribution-ShareAlike 4.0 International License"},{"issue":"5","key":"2307_CR41","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3390\/rs11050523","volume":"11","author":"C Pelletier","year":"2019","unstructured":"Pelletier C, Webb GI, Petitjean F (2019) Temporal convolutional neural network for the classification of satellite image time series. Remote Sens 11(5):523","journal-title":"Remote Sens"},{"key":"2307_CR42","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/BF01100691","volume":"5","author":"M Pogu","year":"1994","unstructured":"Pogu M, Souza de Cursi JE (1994) Global optimization by random perturbation of the gradient method with a fixed parameter. J Global Optim 5:159\u2013180","journal-title":"J Global Optim"},{"issue":"6","key":"2307_CR43","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386\u2013408. https:\/\/doi.org\/10.1037\/h0042519","journal-title":"Psychol Rev"},{"key":"2307_CR44","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1016\/j.procs.2015.02.091","volume":"46","author":"BK Singh","year":"2015","unstructured":"Singh BK, Verma K, Thoke AS (2015) Adaptive gradient descent backpropagation for classification of breast tumors in ultrasound imaging. Procedia Comput Sci 46:1601\u20131609","journal-title":"Procedia Comput Sci"},{"key":"2307_CR45","unstructured":"Stutz D (2014) Understanding convolutional neural networks. Seminar report, Fakult\u00e4t f\u00fcr Mathematik, Informatik und Naturwissenschaften"},{"key":"2307_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5495-7_11","volume-title":"Bio-inspired neurocomputing. Studies in computational intelligence","author":"T Szanda\u0142a","year":"2021","unstructured":"Szanda\u0142a T (2021) Review and comparison of commonly used activation functions for deep neural networks. In: Bhoi A, Mallick P, Liu CM, Balas V (eds) Bio-inspired neurocomputing. Studies in computational intelligence, vol 903. Springer, Singapore. https:\/\/doi.org\/10.1007\/978-981-15-5495-7_11"},{"key":"2307_CR47","doi-asserted-by":"publisher","first-page":"2557","DOI":"10.1007\/s00245-020-09718-8","volume":"84","author":"TT Tuyen","year":"2021","unstructured":"Tuyen TT, Hang-Tuan N (2021) Backtracking gradient descent method and some applications in large scale optimisation. Part 2. Appl Math Optim 84:2557\u20132586","journal-title":"Appl Math Optim"},{"issue":"2","key":"2307_CR48","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/BF00939925","volume":"71","author":"SP Uryas\u2019ev","year":"1991","unstructured":"Uryas\u2019ev SP (1991) New variable-metric algorithms for nondifferentiable optimization problems. J Optim Theory Appl 71(2):359\u2013388","journal-title":"J Optim Theory Appl"},{"key":"2307_CR49","doi-asserted-by":"publisher","first-page":"47","DOI":"10.4467\/20838476SI.18.004.10409","volume":"27","author":"B W\u00f3jcik","year":"2018","unstructured":"W\u00f3jcik B, Maziarka L, Tabor J (2018) Automatic learning rate in gradient descent. Schedae Inf 27:47\u201357","journal-title":"Schedae Inf"},{"issue":"10","key":"2307_CR50","first-page":"29","volume":"8","author":"L Xinhua","year":"2015","unstructured":"Xinhua L, Qian Y (2015) Face recognition based on deep neural network. Int J Signal Process Image Process Pattern Recogn 8(10):29\u201338","journal-title":"Int J Signal Process Image Process Pattern Recogn"},{"key":"2307_CR51","unstructured":"Zeiler MD, Fergus R (2013) Visualizing and understanding convolutional networks. Comput Res Repos. arXiv:abs\/1311.2901"}],"container-title":["Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-023-02307-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40314-023-02307-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-023-02307-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:11:02Z","timestamp":1702325462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40314-023-02307-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["2307"],"URL":"https:\/\/doi.org\/10.1007\/s40314-023-02307-9","relation":{},"ISSN":["2238-3603","1807-0302"],"issn-type":[{"value":"2238-3603","type":"print"},{"value":"1807-0302","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,1]]},"assertion":[{"value":"19 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare. All co-authors have seen and agree with the contents of the manuscript \u201cStochastic Perturbation of Subgradient Algorithm for Nonconvex Deep Neural Networks\u201d and there is no financial interest to report. We certify that the submission is original work and is not under review at any other publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"167"}}