{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T04:06:05Z","timestamp":1747713965069,"version":"3.40.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:00:00Z","timestamp":1743638400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:00:00Z","timestamp":1743638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Liaoning Provincial Education Department Scientific Research Funding Project in 2024","award":["No.LJ212410152077"],"award-info":[{"award-number":["No.LJ212410152077"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61403056"],"award-info":[{"award-number":["No. 61403056"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["No. 2018YFD0901002"],"award-info":[{"award-number":["No. 2018YFD0901002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Appl. Math."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s40314-025-03180-4","type":"journal-article","created":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T01:42:09Z","timestamp":1743817329000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A gradient-based learning method with smoothing group $$L_0$$ regularization for interval perceptron and interval weights"],"prefix":"10.1007","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-4652","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jinru","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuanquan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"3180_CR1","doi-asserted-by":"publisher","first-page":"158820","DOI":"10.1109\/ACCESS.2019.2945545","volume":"7","author":"OI Abiodun","year":"2019","unstructured":"Abiodun OI, Jantan A, Omolara AE et al (2019) Comprehensive review of artificial neural network applications to pattern recognition. IEEE Access 7:158820\u2013158846. https:\/\/doi.org\/10.1109\/ACCESS.2019.2945545","journal-title":"IEEE Access"},{"key":"3180_CR2","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1145\/3498675","volume":"4","author":"MR Baker","year":"1998","unstructured":"Baker MR, Patil RB (1998) Universal approximation theorem for interval neural networks. Reliab Comput 4:235\u2013239. https:\/\/doi.org\/10.1145\/3498675","journal-title":"Reliab Comput"},{"key":"3180_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110068","volume":"136","author":"F Chu","year":"2023","unstructured":"Chu F, Wang G, Wang J et al (2023) Learning broad learning system with controllable sparsity through L0 regularization. Appl Soft Comput 136:110068. https:\/\/doi.org\/10.1016\/j.asoc.2023.110068","journal-title":"Appl Soft Comput"},{"key":"3180_CR4","unstructured":"Cortes C, Mohri M, Rostamizadeh A (2012) L2 regularization for learning kernels. Preprint arXiv:1205.2653"},{"issue":"10","key":"3180_CR5","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1109\/TC.2019.2914438","volume":"68","author":"X Dai","year":"2019","unstructured":"Dai X, Yin H, Jha NK (2019) NeST: A neural network synthesis tool based on a grow-and-prune paradigm. IEEE Trans Comput 68(10):1487\u20131497. https:\/\/doi.org\/10.1109\/TC.2019.2914438","journal-title":"IEEE Trans Comput"},{"issue":"1\u20133","key":"3180_CR6","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/S0925-2312(97)00080-5","volume":"18","author":"GP Drago","year":"1998","unstructured":"Drago GP, Ridella S (1998) Pruning with interval arithmetic perceptron. Neurocomputing 18(1\u20133):229\u2013246. https:\/\/doi.org\/10.1016\/S0925-2312(97)00080-5","journal-title":"Neurocomputing"},{"key":"3180_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113783","volume":"162","author":"M Esteve","year":"2020","unstructured":"Esteve M, Aparicio J, Rabasa A et al (2020) Efficiency analysis trees: a new methodology for estimating production frontiers through decision trees. Expert Syst Appl 162:113783. https:\/\/doi.org\/10.1016\/j.eswa.2020.113783","journal-title":"Expert Syst Appl"},{"issue":"4","key":"3180_CR8","doi-asserted-by":"publisher","first-page":"2385","DOI":"10.1007\/s11063-020-10327-3","volume":"53","author":"A Haldorai","year":"2021","unstructured":"Haldorai A, Ramu A (2021) Canonical correlation analysis based hyper basis feedforward neural network classification for urban sustainability. Neural Process Lett 53(4):2385\u20132401. https:\/\/doi.org\/10.1007\/s11063-020-10327-3","journal-title":"Neural Process Lett"},{"issue":"7","key":"3180_CR9","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.3390\/sym13071147","volume":"13","author":"E Jeczmionek","year":"2021","unstructured":"Jeczmionek E, Kowalski PA (2021) Flattening layer pruning in convolutional neural networks. Symmetry 13(7):1147. https:\/\/doi.org\/10.3390\/sym13071147","journal-title":"Symmetry"},{"key":"3180_CR10","doi-asserted-by":"crossref","unstructured":"Jin H, Wei W, Wang X et\u00a0al (2023) Rethinking learning rate tuning in the era of large language models. In: 2023 IEEE 5th international conference on cognitive machine intelligence (CogMI). IEEE, pp 112\u2013121","DOI":"10.1109\/CogMI58952.2023.00025"},{"key":"3180_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-017-1984-2","volume":"18","author":"T Kang","year":"2017","unstructured":"Kang T, Ding W, Zhang L et al (2017) A biological network-based regularized artificial neural network model for robust phenotype prediction from gene expression data. BMC Bioinf 18:1\u201311. https:\/\/doi.org\/10.1186\/s12859-017-1984-2","journal-title":"BMC Bioinf"},{"key":"3180_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.124143","volume":"254","author":"M Khodayar","year":"2022","unstructured":"Khodayar M, Saffari M, Williams M et al (2022) Interval deep learning architecture with rough pattern recognition and fuzzy inference for short-term wind speed forecasting. Energy 254:124143. https:\/\/doi.org\/10.1016\/j.energy.2022.124143","journal-title":"Energy"},{"issue":"3","key":"3180_CR13","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1080\/10618600.2019.1573687","volume":"28","author":"JC Laria","year":"2019","unstructured":"Laria JC, Aguilera-Morillo MC, Lillo RE (2019) An iterative sparse-group lasso. J Comput Graph Stat 28(3):722\u2013731. https:\/\/doi.org\/10.1080\/10618600.2019.1573687","journal-title":"J Comput Graph Stat"},{"key":"3180_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.fss.2016.07.003","volume":"319","author":"Y Liu","year":"2017","unstructured":"Liu Y, Yang D (2017) Convergence analysis of the batch gradient-based neuro-fuzzy learning algorithm with smoothing L1\/2 regularization for the first-order Takagi\u2013Sugeno system. Fuzzy Sets Syst 319:28\u201349. https:\/\/doi.org\/10.1016\/j.fss.2016.07.003","journal-title":"Fuzzy Sets Syst"},{"key":"3180_CR15","doi-asserted-by":"crossref","unstructured":"Ma Q, Qi C, Zhang H (2022) Batch gradient neuro-fuzzy learning method with smoothing l0 regularization for the first-order takagi\u2013Sugeno system. In: Proceedings of the 2022 9th international conference on wireless communication and sensor networks, pp 11\u201315","DOI":"10.1145\/3514105.3514108"},{"key":"3180_CR16","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.neunet.2019.08.015","volume":"119","author":"R Ma","year":"2019","unstructured":"Ma R, Miao J, Niu L et al (2019) Transformed L1 regularization for learning sparse deep neural networks. Neural Netw 119:286\u2013298","journal-title":"Neural Netw"},{"issue":"1","key":"3180_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/72.478388","volume":"7","author":"JO Moody","year":"1996","unstructured":"Moody JO, Antsaklis PJ (1996) The dependence identification neural network construction algorithm. IEEE Trans Neural Netw 7(1):3\u201315. https:\/\/doi.org\/10.1109\/72.478388","journal-title":"IEEE Trans Neural Netw"},{"key":"3180_CR18","volume-title":"Interval analysis","author":"RE Moore","year":"1966","unstructured":"Moore RE (1966) Interval analysis. Prentice-Hall, Hoboken"},{"key":"3180_CR19","doi-asserted-by":"crossref","unstructured":"Niu D, Zhao Z, Jia M (2021) An interval neural network based on improved differential evolution algorithm. In: 2021 33rd Chinese control and decision conference (CCDC). IEEE","DOI":"10.1109\/CCDC52312.2021.9601380"},{"key":"3180_CR20","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neunet.2022.10.011","volume":"158","author":"J Poyatos","year":"2023","unstructured":"Poyatos J, Molina D, Martinez AD et al (2023) EvoPruneDeepTL: an evolutionary pruning model for transfer learning based deep neural networks. Neural Netws 158:59\u201382. https:\/\/doi.org\/10.1016\/j.neunet.2022.10.011","journal-title":"Neural Netws"},{"key":"3180_CR21","unstructured":"Prato G, Guiroy S, Caballero E et al (2021) Scaling laws for the out-of-distribution generalization of image classifiers. In: ICML 2021 workshop on uncertainty and robustness in deep learning"},{"issue":"3","key":"3180_CR22","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s13748-022-00285-3","volume":"11","author":"H Ramchoun","year":"2022","unstructured":"Ramchoun H, Ettaouil M (2022) Convergence of batch gradient algorithm with smoothing composition of group L0 and L1\/2 regularization for feedforward neural networks. Prog Artif Intell 11(3):269\u2013278. https:\/\/doi.org\/10.1007\/s13748-022-00285-3","journal-title":"Prog Artif Intell"},{"key":"3180_CR23","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.neunet.2019.07.005","volume":"118","author":"J Sadeghi","year":"2019","unstructured":"Sadeghi J, Angelis MD, Patelli E (2019) Efficient training of interval neural networks for imprecise training data. Neural Netw 118:338\u2013351. https:\/\/doi.org\/10.1016\/j.neunet.2019.07.005","journal-title":"Neural Netw"},{"issue":"5","key":"3180_CR24","doi-asserted-by":"publisher","first-page":"127","DOI":"10.14257\/ijca.2013.6.5.12","volume":"6","author":"KK Seo","year":"2013","unstructured":"Seo KK (2013) A simulation study on an artificial neural network based automatic control system of a plant factory. Int J Control Autom 6(5):127\u2013136","journal-title":"Int J Control Autom"},{"issue":"1","key":"3180_CR25","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1162\/neco.1997.9.1.185","volume":"9","author":"R Setiono","year":"1997","unstructured":"Setiono R (1997) A penalty-function approach for pruning feedforward neural networks. Neural Comput 9(1):185\u2013204","journal-title":"Neural Comput"},{"issue":"1","key":"3180_CR26","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1109\/72.363426","volume":"6","author":"R Setiono","year":"1995","unstructured":"Setiono R, Hui L (1995) Use of a quasi-newton method in a feedforward neural network construction algorithm. IEEE Trans Neural Netw 6(1):273\u2013277. https:\/\/doi.org\/10.1109\/72.363426","journal-title":"IEEE Trans Neural Netw"},{"key":"3180_CR27","doi-asserted-by":"crossref","unstructured":"Sunaga T et al (2009) Theory of an interval algebra and its application to numerical analysis. Jpn J Ind Appl Math 26(2)","DOI":"10.1007\/BF03186528"},{"key":"3180_CR28","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.neucom.2018.12.036","volume":"333","author":"Z Tong","year":"2019","unstructured":"Tong Z, Tanaka G (2019) Hybrid pooling for enhancement of generalization ability in deep convolutional neural networks. Neurocomputing 333:76\u201385. https:\/\/doi.org\/10.1016\/j.neucom.2018.12.036","journal-title":"Neurocomputing"},{"key":"3180_CR29","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.ins.2016.11.020","volume":"381","author":"J Wang","year":"2017","unstructured":"Wang J, Cai Q, Chang Q et al (2017) Convergence analyses on sparse feedforward neural networks via group lasso regularization. Inf Sci 381:250\u2013269. https:\/\/doi.org\/10.1016\/j.ins.2016.11.020","journal-title":"Inf Sci"},{"issue":"3","key":"3180_CR30","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1109\/TNNLS.2020.2980383","volume":"32","author":"J Wang","year":"2020","unstructured":"Wang J, Zhang H, Wang J et al (2020) Feature selection using a neural network with group lasso regularization and controlled redundancy. IEEE Trans Neural Netw Learn Syst 32(3):1110\u20131123. https:\/\/doi.org\/10.1109\/TNNLS.2020.2980383","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3180_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2021.121275","volume":"234","author":"S Wang","year":"2021","unstructured":"Wang S, Wang J, Lu H et al (2021) A novel combined model for wind speed prediction\u2013Combination of linear model, shallow neural networks, and deep learning approaches. Energy 234:121275. https:\/\/doi.org\/10.1016\/j.energy.2021.121275","journal-title":"Energy"},{"issue":"POPL","key":"3180_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3498675","volume":"6","author":"Z Wang","year":"2022","unstructured":"Wang Z, Albarghouthi A, Prakriya G et al (2022) Interval universal approximation for neural networks. Proc ACM Program Lang 6(POPL):1\u201329. https:\/\/doi.org\/10.1145\/3498675","journal-title":"Proc ACM Program Lang"},{"key":"3180_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.neunet.2022.03.033","volume":"151","author":"Z Wei","year":"2022","unstructured":"Wei Z, Li Q, Wei J et al (2022) Neural network for a class of sparse optimization with L0-regularization. Neural Netw 151:211\u2013221. https:\/\/doi.org\/10.1016\/j.neunet.2022.03.033","journal-title":"Neural Netw"},{"issue":"1","key":"3180_CR34","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.neunet.2010.09.007","volume":"24","author":"W Wu","year":"2011","unstructured":"Wu W, Wang J, Cheng M et al (2011) Convergence analysis of online gradient method for BP neural networks. Neural Netw 24(1):91\u201398. https:\/\/doi.org\/10.1016\/j.neunet.2010.09.007","journal-title":"Neural Netw"},{"issue":"04","key":"3180_CR35","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1142\/S0219530522500105","volume":"21","author":"Y Xu","year":"2023","unstructured":"Xu Y (2023) Sparse regularization with the L0 norm. Anal Appl 21(04):901\u2013929","journal-title":"Anal Appl"},{"key":"3180_CR36","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/456919","author":"D Yang","year":"2012","unstructured":"Yang D, Wu W (2012) A smoothing interval neural network. Discrete Dyn Nat Soc. https:\/\/doi.org\/10.1155\/2012\/456919","journal-title":"Discrete Dyn Nat Soc"},{"key":"3180_CR37","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s11063-014-9362-9","volume":"42","author":"D Yang","year":"2015","unstructured":"Yang D, Li Z, Liu Y et al (2015) A modified learning algorithm for interval perceptrons with interval weights. Neural Process Lett 42:381\u2013396. https:\/\/doi.org\/10.1007\/s11063-014-9362-9","journal-title":"Neural Process Lett"},{"issue":"2","key":"3180_CR38","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1007\/s11063-022-10956-w","volume":"55","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Wei J, Xu D et al (2023) Batch gradient training method with smoothing group L0 regularization for feedfoward neural networks. Neural Process Lett 55(2):1663\u20131679. https:\/\/doi.org\/10.1007\/s11063-022-10956-w","journal-title":"Neural Process Lett"}],"container-title":["Computational and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-025-03180-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40314-025-03180-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40314-025-03180-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T14:10:36Z","timestamp":1747663836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40314-025-03180-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,3]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["3180"],"URL":"https:\/\/doi.org\/10.1007\/s40314-025-03180-4","relation":{},"ISSN":["2238-3603","1807-0302"],"issn-type":[{"type":"print","value":"2238-3603"},{"type":"electronic","value":"1807-0302"}],"subject":[],"published":{"date-parts":[[2025,4,3]]},"assertion":[{"value":"14 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2025","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 declare that there is no conflict of interest in the manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"221"}}