{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T04:03:27Z","timestamp":1750997007287,"version":"3.41.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61771001"],"award-info":[{"award-number":["61771001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"DOI":"10.1007\/s11063-025-11766-6","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T21:09:08Z","timestamp":1748466548000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AdamRAG: Adaptive Algorithm with Ravine Method for Training Deep Neural Networks"],"prefix":"10.1007","volume":"57","author":[{"given":"Yifan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Di","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Hongyi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chengwei","family":"Pan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"11766_CR1","doi-asserted-by":"crossref","unstructured":"Bangyal WH, Iqbal M, Bashir A, Ubakanma G (2023) Polarity classification of twitter data using machine learning approach. In: 2023 International Conference on Human-Centered Cognitive Systems (HCCS), pp. 1\u20136. IEEE","DOI":"10.1109\/HCCS59561.2023.10452567"},{"key":"11766_CR2","doi-asserted-by":"crossref","unstructured":"Shafqat Z, Iqbal M, Bangyal WH, Almakhles D (2022) Opinion mining of politics and inflation using roman urdu dataset. In: 2022 Human-Centered Cognitive Systems (HCCS), pp. 1\u20136. IEEE","DOI":"10.1109\/HCCS55241.2022.10090276"},{"issue":"01","key":"11766_CR3","doi-asserted-by":"publisher","first-page":"2140007","DOI":"10.1142\/S0218213021400078","volume":"30","author":"C Dai","year":"2021","unstructured":"Dai C, Che H, Leung M-F (2021) A neurodynamic optimization approach for l 1 minimization with application to compressed image reconstruction. International Journal on Artificial Intelligence Tools 30(01):2140007","journal-title":"International Journal on Artificial Intelligence Tools"},{"key":"11766_CR4","doi-asserted-by":"crossref","unstructured":"Ul\u00a0Hassan N, Bangyal WH, Ali\u00a0Khan MS, Nisar K, Ag.\u00a0Ibrahim AA, Rawat DB (2021) Improved opposition-based particle swarm optimization algorithm for global optimization. Symmetry 13(12), 2280","DOI":"10.3390\/sym13122280"},{"issue":"2","key":"11766_CR5","doi-asserted-by":"publisher","first-page":"4199","DOI":"10.32604\/cmc.2022.020449","volume":"70","author":"N Bacanin","year":"2022","unstructured":"Bacanin N, Alhazmi K, Zivkovic M, Venkatachalam K, Bezdan T, Nebhen J (2022) Training multi-layer perceptron with enhanced brain storm optimization metaheuristics. Computers, Materials & Continua 70(2):4199\u20134215","journal-title":"Computers, Materials & Continua"},{"issue":"5","key":"11766_CR6","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1007\/s40815-021-01191-x","volume":"24","author":"N Bacanin","year":"2022","unstructured":"Bacanin N, Bezdan T, Al-Turjman F, Rashid TA (2022) Artificial flora optimization algorithm with genetically guided operators for feature selection and neural network training. International Journal of Fuzzy Systems 24(5):2538\u20132559","journal-title":"International Journal of Fuzzy Systems"},{"issue":"2","key":"11766_CR7","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","volume":"4","author":"K Hornik","year":"1991","unstructured":"Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural networks 4(2):251\u2013257","journal-title":"Neural networks"},{"key":"11766_CR8","unstructured":"Zeng J, Lau TT-K, Lin S, Yao Y (2019) Global convergence of block coordinate descent in deep learning. In: International Conference on Machine Learning, pp. 7313\u20137323. PMLR"},{"key":"11766_CR9","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1109\/TSP.2019.2959240","volume":"68","author":"Y Yang","year":"2020","unstructured":"Yang Y, Pesavento M, Luo Z-Q, Ottersten B (2020) Inexact block coordinate descent algorithms for nonsmooth nonconvex optimization. IEEE Transactions on Signal Processing 68:947\u2013961","journal-title":"IEEE Transactions on Signal Processing"},{"key":"11766_CR10","unstructured":"Cai X, Song C, Wright S, Diakonikolas J (2023) Cyclic block coordinate descent with variance reduction for composite nonconvex optimization. In: International Conference on Machine Learning, pp. 3469\u20133494. PMLR"},{"key":"11766_CR11","unstructured":"Ji K, Wang Z, Zhou Y, Liang Y (2019) Improved zeroth-order variance reduced algorithms and analysis for nonconvex optimization. In: International Conference on Machine Learning, pp. 3100\u20133109. PMLR"},{"key":"11766_CR12","first-page":"12868","volume":"35","author":"X Wang","year":"2022","unstructured":"Wang X, Guo W, Su J, Yang X, Yan J (2022) Zarts: On zero-order optimization for neural architecture search. Advances in Neural Information Processing Systems 35:12868\u201312880","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11766_CR13","unstructured":"Chen L, Xu J, Luo L (2023) Faster gradient-free algorithms for nonsmooth nonconvex stochastic optimization. In: International Conference on Machine Learning, pp. 5219\u20135233. PMLR"},{"issue":"4","key":"11766_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-021-02224-6","volume":"52","author":"W Yuan","year":"2022","unstructured":"Yuan W, Hu F, Lu L (2022) A new non-adaptive optimization method: Stochastic gradient descent with momentum and difference. Applied Intelligence 52(4):1\u201315","journal-title":"Applied Intelligence"},{"issue":"2","key":"11766_CR15","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/0893-6080(94)00067-V","volume":"8","author":"SJ Perantonis","year":"1995","unstructured":"Perantonis SJ, Karras DA (1995) An efficient constrained learning algorithm with momentum acceleration. Neural Networks 8(2):237\u2013249","journal-title":"Neural Networks"},{"key":"11766_CR16","unstructured":"Nesterov Y (1983) A method for unconstrained convex minimization problem with the rate of convergence o (1\/k2). In: Dokl. Akad. Nauk. SSSR, vol. 269, p. 543"},{"issue":"7","key":"11766_CR17","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. Journal of machine learning research 12(7):2121\u20132159","journal-title":"Journal of machine learning research"},{"key":"11766_CR18","unstructured":"D\u00e9fossez A, Bottou L, Bach F, Usunier N (2022) A simple convergence proof of adam and adagrad. Transactions on Machine Learning Research, 1\u201330"},{"key":"11766_CR19","unstructured":"Tieleman T (2012) Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning 4(2), 26"},{"key":"11766_CR20","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.neunet.2021.02.011","volume":"139","author":"D Xu","year":"2021","unstructured":"Xu D, Zhang S, Zhang H, Mandic DP (2021) Convergence of the rmsprop deep learning method with penalty for nonconvex optimization. Neural Networks 139:17\u201323","journal-title":"Neural Networks"},{"key":"11766_CR21","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 1\u201315"},{"key":"11766_CR22","unstructured":"Reddi SJ, Kale S, Kumar S (2019) On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237, 1\u201323"},{"issue":"3","key":"11766_CR23","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.1007\/s10489-024-05303-6","volume":"54","author":"W Jiang","year":"2024","unstructured":"Jiang W, Liang Y, Jiang Z, Xu D, Zhou L (2024) Abngrad: adaptive step size gradient descent for optimizing neural networks. Applied Intelligence 54(3):2361\u20132378","journal-title":"Applied Intelligence"},{"key":"11766_CR24","unstructured":"Luo L, Xiong Y, Liu Y, Sun X (2019) Adaptive gradient methods with dynamic bound of learning rate. arXiv preprint arXiv:1902.09843, 1\u201319"},{"issue":"15","key":"11766_CR25","doi-asserted-by":"publisher","first-page":"17691","DOI":"10.1007\/s11227-023-05338-5","volume":"79","author":"Y Liu","year":"2023","unstructured":"Liu Y, Li D (2023) Adaxod: a new adaptive and momental bound algorithm for training deep neural networks. The Journal of Supercomputing 79(15):17691\u201317715","journal-title":"The Journal of Supercomputing"},{"key":"11766_CR26","unstructured":"Ding J, Ren X, Luo R, Sun X (2019) An adaptive and momental bound method for stochastic learning. arXiv preprint arXiv:1910.12249, 1\u20138"},{"key":"11766_CR27","unstructured":"Dozat T (2016) Incorporating nesterov momentum into adam, 1\u20134"},{"key":"11766_CR28","first-page":"295","volume":"137","author":"I Gelfand","year":"1961","unstructured":"Gelfand I, Zejtlin M (1961) Printszip nelokalnogo poiska v sistemah avtomatich, optimizatsii, dokl. AN SSSR 137:295\u2013298","journal-title":"AN SSSR"},{"issue":"5","key":"11766_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak BT (1964) Some methods of speeding up the convergence of iteration methods. Ussr computational mathematics and mathematical physics 4(5):1\u201317","journal-title":"Ussr computational mathematics and mathematical physics"},{"issue":"3","key":"11766_CR30","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1137\/22M1474357","volume":"32","author":"H Attouch","year":"2022","unstructured":"Attouch H, Fadili J (2022) From the ravine method to the nesterov method and vice versa: a dynamical system perspective. SIAM Journal on Optimization 32(3):2074\u20132101","journal-title":"SIAM Journal on Optimization"},{"key":"11766_CR31","unstructured":"Attouch H, Fadili J, Kungurtsev V (2024) The stochastic ravine accelerated gradient method with general extrapolation coefficients. arXiv preprint arXiv:2403.04860, 1\u201343"},{"key":"11766_CR32","unstructured":"Jiang Y, Liu J, Xu D, Mandic DP (2023) Uadam: Unified adam-type algorithmic framework for non-convex stochastic optimization. arXiv preprint arXiv:2305.05675, 1\u201328"},{"issue":"3","key":"11766_CR33","doi-asserted-by":"publisher","first-page":"2458","DOI":"10.1002\/num.22726","volume":"37","author":"H Ko\u00e7ak","year":"2021","unstructured":"Ko\u00e7ak H (2021) A combined meshfree exponential rosenbrock integrator for the third-order dispersive partial differential equations. Numerical Methods for Partial Differential Equations 37(3):2458\u20132468","journal-title":"Numerical Methods for Partial Differential Equations"},{"key":"11766_CR34","unstructured":"Maas A, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150"},{"issue":"11","key":"11766_CR35","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 (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"11766_CR36","unstructured":"Krizhevsky A, Hinton G, et al (2009) Learning multiple layers of features from tiny images, 1\u201360"},{"key":"11766_CR37","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, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11766-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-025-11766-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11766-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T05:57:38Z","timestamp":1750917458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-025-11766-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["11766"],"URL":"https:\/\/doi.org\/10.1007\/s11063-025-11766-6","relation":{},"ISSN":["1573-773X"],"issn-type":[{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"9 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The data used in this study were obtained from publicly available datasets. The dataset is anonymized and does not contain any personally identifiable information. Informed consent was obtained from all individual participants included in the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}},{"value":"The authors declare that there is no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"53"}}