{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T18:43:45Z","timestamp":1778525025936,"version":"3.51.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00521-025-11242-1","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T18:57:09Z","timestamp":1746557829000},"page":"14005-14028","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Stochastic gradient sampling for enhancing neural networks training"],"prefix":"10.1007","volume":"37","author":[{"given":"Juyoung","family":"Yun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"issue":"7553","key":"11242_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"11242_CR2","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep Learning. MIT Press, Cambridge, MA"},{"key":"11242_CR3","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747. Available at: https:\/\/arxiv.org\/abs\/1609.04747"},{"key":"11242_CR4","doi-asserted-by":"crossref","unstructured":"Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT\u20192010, Springer, Berlin, Heidelberg, pp\u00a0177\u2013186","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"11242_CR5","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. Available at: https:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"2","key":"11242_CR6","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw Mach Learn 4(2):26","journal-title":"COURSERA: Neural Netw Mach Learn"},{"key":"11242_CR7","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi J, 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":"11242_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp\u00a0770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11242_CR9","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Available at: https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"11242_CR10","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), IEEE, pp\u00a04510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"11242_CR11","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et\u00a0al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020). Available at: https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"11242_CR12","volume-title":"Elements of information theory","author":"TM Cover","year":"2006","unstructured":"Cover TM, Thomas JA (2006) Elements of information theory. John Wiley & Sons, Hoboken, NJ"},{"issue":"1","key":"11242_CR13","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian N (1999) On the momentum term in gradient descent learning algorithms. Neural Netw 12(1):145\u2013151","journal-title":"Neural Netw"},{"key":"11242_CR14","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"11242_CR15","doi-asserted-by":"crossref","unstructured":"Yong H, Huang J, Hua X, Zhang L (2020) Gradient centralization: a new optimization technique for deep neural networks. arXiv preprint  arXiv:2004.01461","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"11242_CR16","unstructured":"Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In Proceedings of the 30th international conference on machine learning (ICML-13), pp\u00a01310\u20131318"},{"key":"11242_CR17","unstructured":"Wen W, Wu C, Wang Y, Chen Y, Li H (2017) Learning structured sparsity in deep neural networks. In Adv Neural Inform Process Syst, pp\u00a02074\u20132082"},{"issue":"6","key":"11242_CR18","first-page":"61","volume":"32","author":"P Zhao","year":"2015","unstructured":"Zhao P, Zhang T, Chen Y (2015) Stochastic learning and optimization. IEEE Signal Process Magaz 32(6):61\u201374","journal-title":"IEEE Signal Process Magaz"},{"key":"11242_CR19","unstructured":"Burke JV, Curtis FE, Lewis AS, Overton ML, Sim\u00f5es LE (2018) Gradient sampling methods for nonsmooth optimization. arXiv preprint arXiv:1804.11003. Available at: https:\/\/arxiv.org\/abs\/1804.11003"},{"key":"11242_CR20","unstructured":"Tripathi R, Singh B (2020) Rso: A gradient free sampling based approach for training deep neural networks. arXiv preprint arXiv:2005.05955. Technical Report"},{"key":"11242_CR21","volume-title":"Pattern Recognition Maching Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM (2006) Pattern Recognition Maching Learning. Springer, New York, NY"},{"issue":"3","key":"11242_CR22","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379\u2013423","journal-title":"Bell Syst Tech J"},{"key":"11242_CR23","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D (2015) Weight uncertainty in neural networks. In Proceedings of the 32nd international conference on machine learning (ICML), pp\u00a01613\u20131622"},{"key":"11242_CR24","unstructured":"Chaudhari P, Choromanska A, Soatto S, LeCun Y, Baldassi C, Borgs C, Chayes J, Sagun L, Zecchina R (2016) Entropy-sgd: Biasing gradient descent into wide valleys. In Proceedings of the 19th international conference on artificial intelligence and statistics (AISTATS), pp\u00a0839\u2013848"},{"key":"11242_CR25","unstructured":"Kingma DP, Welling M (2014) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"11242_CR26","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. In International conference on machine learning (ICML), PMLR, pp\u00a01050\u20131059"},{"key":"11242_CR27","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Tech. rep., Citeseer, Technical Report"},{"key":"11242_CR28","volume-title":"Principal Component Analysis","author":"I Jolliffe","year":"2016","unstructured":"Jolliffe I, Cadima J (2016) Principal Component Analysis. Springer, New York, NY"},{"key":"11242_CR29","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention (MICCAI), Springer, pp\u00a0234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11242_CR30","volume-title":"The oxford-iiit pet dataset","author":"OM Parkhi","year":"2012","unstructured":"Parkhi OM, Vedaldi A, Zisserman A, Jawahar CV (2012) The oxford-iiit pet dataset. University of Oxford, Department of Engineering Science"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11242-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11242-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11242-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:28:02Z","timestamp":1751012882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11242-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,6]]},"references-count":30,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11242"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11242-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,6]]},"assertion":[{"value":"14 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}