{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:54:21Z","timestamp":1776783261993,"version":"3.51.2"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"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":["Appl Intell"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s10489-022-04353-y","type":"journal-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T05:02:40Z","timestamp":1672894960000},"page":"17429-17443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Regularization-based pruning of irrelevant weights in deep neural architectures"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4498-1026","authenticated-orcid":false,"given":"Giovanni","family":"Bonetta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Ribero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rossella","family":"Cancelliere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,5]]},"reference":[{"key":"4353_CR1","doi-asserted-by":"crossref","unstructured":"Zhang K, Gool LV, Timofte R (2020) Deep unfolding network for image super-resolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00328"},{"key":"4353_CR2","doi-asserted-by":"crossref","unstructured":"He T, Zhang Z, Zhang H, Zhang Z, Xie J, Li M (2019) Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00065"},{"key":"4353_CR3","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\/CVF conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"4353_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4353_CR5","doi-asserted-by":"crossref","unstructured":"Guo L, Liu J, Zhu X, Yao P, Lu S, Lu H (2020) Normalized and geometry-aware self-attention network for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"4353_CR6","doi-asserted-by":"crossref","unstructured":"Feng Y, Ma L, Liu W, Luo J (2019) Unsupervised image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00425"},{"key":"4353_CR7","doi-asserted-by":"crossref","unstructured":"Puduppully R, Dong L, Lapata M (2019) Data-to-text generation with content selection and planning. In: Proceedings of the thirty-third conference on artificial intelligence, AAAI, Honolulu, Hawaii, USA, pp 6908\u20136915","DOI":"10.1609\/aaai.v33i01.33016908"},{"key":"4353_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.csl.2019.06.009","volume":"59","author":"O Dusek","year":"2020","unstructured":"Dusek O, Novikova J, Rieser V (2020) Evaluating the state-of-the-art of end-to-end natural language generation: the E2E NLG challenge. Comput Speech Lang 59:123\u2013156","journal-title":"Comput Speech Lang"},{"key":"4353_CR9","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 31, pp 6000\u20136010"},{"key":"4353_CR10","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: 3rd International conference on learning representations ICLR, San Diego, CA, USA"},{"key":"4353_CR11","unstructured":"Han S, Pool J, Tran J, Dally WJ (2015) Learning both weights and connections for efficient neural network. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28, pp 1135\u20131143"},{"key":"4353_CR12","unstructured":"Ullrich K, Meeds E, Welling M (2017) Soft weight-sharing for neural network compression. In: 5th International Conference on Learning Representations, ICLR, Toulon, France"},{"key":"4353_CR13","unstructured":"Sanh V, Wolf T, Rush AM (2020) Movement pruning: adaptive sparsity by fine-tuning. Adv Neural Inf Process Syst, vol 34"},{"key":"4353_CR14","doi-asserted-by":"crossref","unstructured":"Liu J, Wang Y, Qiao Y (2017) Sparse deep transfer learning for convolutional neural network. In: The thirty-first AAAI conference on artificial intelligence, AAAI","DOI":"10.1609\/aaai.v31i1.10801"},{"key":"4353_CR15","unstructured":"Tartaglione E, Leps\u00f8y S, Fiandrotti A , Francini G (2018) Learning sparse neural networks via sensitivity-driven regularization. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems, vol 32, NeurIPS"},{"key":"4353_CR16","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.neunet.2021.11.029","volume":"146","author":"E Tartaglione","year":"2022","unstructured":"Tartaglione E, Bragagnolo A, Fiandrotti A, Grangetto M (2022) LOSs-based sensitivity regularization: towards deep sparse neural networks. Neural Netw 146:230\u2013237","journal-title":"Neural Netw"},{"key":"4353_CR17","unstructured":"Gomez AN, Zhang I, Swersky K, Gal Y, Hinton GE (2019) Learning sparse networks using targeted dropout. arXiv:1905.13678"},{"key":"4353_CR18","doi-asserted-by":"crossref","unstructured":"Lin S et al (2018) Accelerating convolutional networks via global & dynamic filter pruning, proceedings of the 27th international joint conference on artificial intelligence IJCAI","DOI":"10.24963\/ijcai.2018\/336"},{"issue":"2","key":"4353_CR19","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/TNNLS.2019.2906563","volume":"31","author":"S Lin","year":"2020","unstructured":"Lin S et al (2020) Toward compact convnets via structure-sparsity regularized filter pruning. IEEE Trans Neural Netw Learn Syst 31(2):574\u2013588","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4353_CR20","unstructured":"Lin C et al (2018) Synaptic strength for convolutional neural network. Adv Neural Inf Process Syst, vol 32 neurIPS"},{"key":"4353_CR21","doi-asserted-by":"publisher","first-page":"175703","DOI":"10.1109\/ACCESS.2019.2957203","volume":"7","author":"Z Wang","year":"2019","unstructured":"Wang Z, Lin S, Xie J, Lin Y (2019) Pruning Blocks for CNN compression and acceleration via online ensemble distillation. IEEE Access 7:175703\u2013175716","journal-title":"IEEE Access"},{"key":"4353_CR22","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TIP.2020.3035028","volume":"30","author":"G Ding","year":"2021","unstructured":"Ding G, Zhang S, Jia Z, Zhong J, Han J (2021) Where to prune: using LSTM to guide data-dependent soft pruning. IEEE Trans Image Process 30:293\u2013304","journal-title":"IEEE Trans Image Process"},{"issue":"7","key":"4353_CR23","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.neucom.2021.10.009","volume":"467","author":"J Zhu","year":"2022","unstructured":"Zhu J, Pei J (2022) Progressive kernel pruning with saliency mapping of input-output channels. Neurocomputing 467(7):360\u2013378","journal-title":"Neurocomputing"},{"issue":"3","key":"4353_CR24","first-page":"1","volume":"52","author":"J Zhu","year":"2022","unstructured":"Zhu J, Pei J, Progressive kernel pruning CNN (2022) Compression method with an adjustable input channel. Appl Intell 52(3):1\u201322","journal-title":"Appl Intell"},{"key":"4353_CR25","doi-asserted-by":"crossref","unstructured":"Huang Z, Wang N (2018) Data-driven sparse structure selection for deep neural. Proceedings of the 15th european conference on computer vision ECCV","DOI":"10.1007\/978-3-030-01270-0_19"},{"issue":"8","key":"4353_CR26","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1109\/TCYB.2019.2933477","volume":"50","author":"Y He","year":"2020","unstructured":"He Y, Dong X, Kang G, Fu Y, Yan C, Yang Y (2020) Asymptotic soft filter pruning for deep convolutional neural networks. IEEE Trans Cybern 50(8):3594\u20133604","journal-title":"IEEE Trans Cybern"},{"key":"4353_CR27","doi-asserted-by":"crossref","unstructured":"Lin M et al (2020) HRank: filter pruning using high-rank feature map. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1526\u20131535","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"4353_CR28","unstructured":"Zhuang Z, Tan M, Zhuang B, Liu J, Guo Y, Wu Q, Huang J, Zhu J (2018) Discrimination-aware channel pruning for deep neural networks. In: Proceedings of the 32nd international conference on neural information processing systems (NIPS\u201918). Red Hook, NY, USA, pp 883\u2013894"},{"key":"4353_CR29","unstructured":"Molchanov D, Ashukha A, Vetrov DP (2017) Variational dropout sparsifies deep neural networks. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning, ICML, pp 2498\u20132507"},{"key":"4353_CR30","doi-asserted-by":"crossref","unstructured":"Salehinejad H, Valaee S (2021) EDRopout: energy-based dropout and pruning of deep neural networks. IEEE Trans Neural Netw Learn:1\u201314","DOI":"10.1109\/TNNLS.2021.3069970"},{"key":"4353_CR31","unstructured":"Lee N, Ajanthan T, Torr PHS (2019) Snip: single-shot network pruning based on connection sensitivity. In: Proceedings of the 7th international conference on learning representations, ICLR 2019, New Orleans, LA, USA"},{"key":"4353_CR32","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient dnns. In: Lee DD, Sugiyama M, von Luxburg U, Guyon I, Garnett R (eds) Advances in neural information processing systems, vol 29, Barcelona, Spain, pp 1379\u20131387"},{"key":"4353_CR33","unstructured":"Gale T, Elsen E, Hooker S (2019) The state of sparsity in deep neural networks. arXiv:1902.09574"},{"key":"4353_CR34","volume-title":"Deep Learning, Adaptive computation and machine learning series","author":"IJ Goodfellow","year":"2016","unstructured":"Goodfellow IJ, Bengio Y, Courville AC (2016) Deep Learning, Adaptive computation and machine learning series. The MIT Press, Massachusetts Institute of Technology, Cambridge"},{"key":"4353_CR35","first-page":"1035","volume":"4","author":"AN Tikhonov","year":"1963","unstructured":"Tikhonov AN (1963) Solution of incorrectly formulated problems and the regularization method. Soviet Math Dokl 4:1035\u20131038","journal-title":"Soviet Math Dokl"},{"key":"4353_CR36","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics (ACL), Philadelphia, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"4353_CR37","unstructured":"LeCun Y, Cortes C (1990) MNIST handwritten digit database"},{"key":"4353_CR38","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747"},{"key":"4353_CR39","unstructured":"Alex Krizhevsky VN, Hinton G (2009) CIFAR RGB image dataset"},{"issue":"11","key":"4353_CR40","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1109\/TPAMI.2008.128","volume":"30","author":"A Torralba","year":"2008","unstructured":"Torralba A, Fergus R, Freeman WT (2008) 80 Million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans Pattern Anal Mach Intell 30(11):1958\u20131970","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4353_CR41","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"11","key":"4353_CR42","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) Wordnet: a lexical database for english. Commun ACM 38(11):39\u201341","journal-title":"Commun ACM"},{"issue":"4","key":"4353_CR43","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":"4353_CR44","unstructured":"Louizos C, Welling M, Kingma DP (2018) Learning sparse neural networks through l_0 regularization. In: 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, 30 April - 3 May 2018, conference track proceedings, openreview.net"},{"key":"4353_CR45","unstructured":"Michel P, Levy O, Neubig G (2019) Are sixteen heads really better than one?. In: wallach H, Larochelle H, Beygelzimer A, D'Alch\u00e9-Buc F, Fox E, Garnett R (eds) Advances in neural information processing systems, vol 33"},{"key":"4353_CR46","doi-asserted-by":"crossref","unstructured":"Voita E, Talbot D, Moiseev F, Sennrich R, Titov I (2019) Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of the 57th annual meeting of the association for computational linguistics (ACL), Stroudsburg, PA, USA, pp 5797\u20135808","DOI":"10.18653\/v1\/P19-1580"},{"key":"4353_CR47","doi-asserted-by":"crossref","unstructured":"Byrne B, Krishnamoorthi K, Sankar C, Neelakantan A, Goodrich B, Duckworth D, Yavuz S, Dubey A, Kim K, Cedilnik A (2019) Taskmaster-1: toward a realistic and diverse dialog dataset. In: Inui K, Jiang J, Ng V, Wan X (eds) Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing EMNLP-IJCNLP, Hong Kong, China, pp 4515\u20134524","DOI":"10.18653\/v1\/D19-1459"},{"key":"4353_CR48","doi-asserted-by":"crossref","unstructured":"Bojar O, Buck C, Federmann C, Haddow B, Koehn P, Leveling J, Monz C, Pecina P, Post M, Saint-Amand H, Soricut R, Specia L, Tamchyna A (2014) Proceedings of the ninth workshop on statistical machine translation, association for computational linguistics, Baltimore, Maryland, USA, pp 12\u201358","DOI":"10.3115\/v1\/W14-3302"},{"key":"4353_CR49","unstructured":"Koehn P (2005) Europarl: a parallel corpus for statistical machine translation. In: Proceedings of the tenth machine translation summit, AAMT, Phuket, Thailand, pp 79\u201386"},{"key":"4353_CR50","unstructured":"Tiedemann J (2012) Parallel data, tools and interfaces in opus. In: Proceedings of the eight international conference on language resources and evaluation (LREC\u201912), european language resources association (ELRA), Istanbul, Turkey"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04353-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04353-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04353-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T12:09:54Z","timestamp":1688472594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04353-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,5]]},"references-count":50,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["4353"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04353-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,5]]},"assertion":[{"value":"18 November 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}