{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:10:43Z","timestamp":1763341843527,"version":"3.45.0"},"reference-count":34,"publisher":"Tech Science Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.061913","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T04:19:16Z","timestamp":1742185156000},"page":"1855-1879","source":"Crossref","is-referenced-by-count":0,"title":["Deterministic Convergence Analysis for GRU Networks via Smoothing Regularization"],"prefix":"10.32604","volume":"83","author":[{"given":"Qian","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Qian","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Dengxiu","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"Proceedings of the 2018 10th International Conference on Machine Learning and Computing","first-page":"26","article-title":"A neural network architecture combining gated recurrent unit (GRU) and support vector machine (SVM) for intrusion detection in network traffic data","author":"Agarap","year":"2018"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1109\/72.883412","article-title":"A recurrent neural network for nonlinear optimization with a continuously differentiable objective function and bound constraints","volume":"11","author":"Liang","year":"2000","journal-title":"IEEE Transact Neural Netw"},{"key":"ref3","first-page":"31","article-title":"Untersuchungen zu dynamischen neuronalen Netzen","volume":"91","author":"Hochreiter","year":"1991","journal-title":"Diploma, Technische Universit\u00e4t M\u00fcnchen"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Transact Neural Netw"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:14061078. 2014.","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"Deep learning","year":"2016","author":"Goodfellow","key":"ref7"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"235","DOI":"10.2478\/jaiscr-2019-0006","article-title":"Performance evaluation of deep neural networks applied to speech recognition: rNN, LSTM and GRU","volume":"9","author":"Shewalkar","year":"2019","journal-title":"J Artif Intell Soft Comput Res"},{"key":"ref9","first-page":"1789","article-title":"An efficient long short-term memory and gated recurrent unit based smart vessel trajectory prediction using automatic identification system data","volume":"81","author":"Zaman","year":"2024","journal-title":"Comput Mater Contin"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J Big Data"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"6391","DOI":"10.1007\/s10462-021-09975-1","article-title":"A systematic review on overfitting control in shallow and deep neural networks","volume":"54","author":"Bejani","year":"2021","journal-title":"Artif Intel Rev"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/S0893-6080(96)00086-X","article-title":"Two strategies to avoid overfitting in feedforward networks","volume":"10","author":"Schittenkopf","year":"1997","journal-title":"Neural Netw"},{"key":"ref13","unstructured":"Li H, Kadav A, Durdanovic I, Samet H, Graf HP. Pruning filters for efficient convnets. arXiv:160808710. 2016."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1162\/neco.1995.7.2.219","article-title":"Regularization theory and neural networks architectures","volume":"7","author":"Girosi","year":"1995","journal-title":"Neural Comput"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"111327","DOI":"10.1016\/j.knosys.2023.111327","volume":"284","author":"Quasdane","year":"2024","journal-title":"Knowl Based Syst"},{"key":"ref16","unstructured":"Van Laarhoven T. L2 regularization versus batch and weight normalization. arXiv:170605350. 2017."},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3510413","article-title":"Avoiding overfitting: a survey on regularization methods for convolutional neural networks","volume":"54","author":"Santos","year":"2022","journal-title":"ACM Comput Surv"},{"key":"ref18","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"10890","article-title":"R-drop: regularized dropout for neural networks","volume":"34","author":"Wu","year":"2021","journal-title":"Adv Neural Inform Process Syst"},{"key":"ref20","first-page":"2981","article-title":"Neural machine translation models with attention-based dropout layer","volume":"75","author":"Israr","year":"2023","journal-title":"Comput Mater Contin"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1111\/j.1467-9868.2007.00607.x","volume":"69","author":"Park","year":"2007","journal-title":"J Royal Statist Soc Ser B: Statist Method"},{"key":"ref22","first-page":"1310","article-title":"The impact of regularization on high-dimensional logistic regression","volume":"32","author":"Salehi","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1109\/TII.2021.3065377","article-title":"Novel L1 regularized extreme learning machine for soft-sensing of an industrial process","volume":"18","author":"Shi","year":"2021","journal-title":"IEEE Transact Indust Inform"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.neucom.2012.02.029","article-title":"Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks","volume":"89","author":"Zhang","year":"2012","journal-title":"Neurocomputing"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.neunet.2012.04.013","article-title":"Computational properties and convergence analysis of BPNN for cyclic and almost cyclic learning with penalty","volume":"33","author":"Wang","year":"2012","journal-title":"Neural Netw"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.ins.2020.12.014","article-title":"Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network","volume":"553","author":"Kang","year":"2021","journal-title":"Inform Sci"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"109656","DOI":"10.1016\/j.patcog.2023.109656","volume":"141","author":"Yu","year":"2023","journal-title":"Pattern Recognit"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.asoc.2017.07.059","article-title":"Convergence analysis of BP neural networks via sparse response regularization","volume":"61","author":"Wang","year":"2017","journal-title":"Appl Soft Comput"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"18687","DOI":"10.1109\/TNNLS.2023.3319989","article-title":"Convergence analysis of online gradient method for high-order neural networks and their sparse optimization","volume":"35","author":"Fan","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"109858","DOI":"10.1016\/j.knosys.2022.109858","volume":"257","author":"Kang","year":"2022","journal-title":"Knowl Based Syst"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"28742","DOI":"10.1109\/ACCESS.2020.3048235","article-title":"Convergence of a gradient-based learning algorithm with penalty for ridge polynomial neural networks","volume":"9","author":"Fan","year":"2021","journal-title":"IEEE Access"},{"key":"ref32","series-title":"2020 International Workshop on Electronic Communication and Artificial Intelligence (IWECAI)","first-page":"98","article-title":"LSTM and GRU neural network performance comparison study: taking yelp review dataset as an example","author":"Yang","year":"2020"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.neunet.2019.08.015","volume":"119","author":"Ma","year":"2019","journal-title":"Neural Netw"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"3532","DOI":"10.1137\/110856204","volume":"51","author":"Campi","year":"2013","journal-title":"SIAM J Cont Optimiza"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-83-2\/TSP_CMC_61913\/TSP_CMC_61913.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:07:40Z","timestamp":1763341660000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v83n2\/60566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.061913","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}