{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:59:41Z","timestamp":1775303981558,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s00521-018-3922-2","type":"journal-article","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T22:48:35Z","timestamp":1544482115000},"page":"1713-1731","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Customised ensemble methodologies for deep learning: Boosted Residual Networks and related approaches"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8918-2389","authenticated-orcid":false,"given":"Alan","family":"Mosca","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George D.","family":"Magoulas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"key":"3922_CR1","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv:1512.03385"},{"key":"3922_CR2","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. arXiv:1603.05027","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"3922_CR3","unstructured":"Schapire RE, Freund Y (1996) Experiments with a new boosting algorithm. In: Machine learning: proceedings of the thirteenth international conference, pp 148\u2013156"},{"issue":"2","key":"3922_CR4","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1023\/A:1007607513941","volume":"40","author":"TG Dietterich","year":"2000","unstructured":"Dietterich TG (2000) An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn 40(2):139\u2013157","journal-title":"Mach Learn"},{"key":"3922_CR5","unstructured":"Tram\u00e8r F, Kurakin A, Papernot N, Goodfellow I, Boneh D, McDaniel P (2017) Ensemble adversarial training: attacks and defenses. arXiv:1705.07204"},{"key":"3922_CR6","doi-asserted-by":"crossref","unstructured":"Mosca A, Magoulas GD (2018) Distillation of deep learning ensembles as a regularisation method. In: Advances in hybridization of intelligent methods, Springer, pp 97\u2013118","DOI":"10.1007\/978-3-319-66790-4_6"},{"key":"3922_CR7","doi-asserted-by":"crossref","unstructured":"Mosca A, Magoulas G (2017) Boosted residual networks. In: EANN. 18th international conference on engineering applications of neural networks","DOI":"10.1007\/978-3-319-65172-9_12"},{"issue":"2","key":"3922_CR8","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1023\/A:1018054314350","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24(2):123\u2013140","journal-title":"Mach Learn"},{"key":"3922_CR9","unstructured":"Mosca A, Magoulas G (2016) Deep incremental boosting. In: Benzmuller C, Sutcliffe G, Rojas R (eds) GCAI 2016. 2nd global conference on artificial intelligence. EPiC series in computing, EasyChair, vol\u00a041, pp 293\u2013302"},{"issue":"3","key":"3922_CR10","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/0167-8191(90)90086-O","volume":"14","author":"D Whitley","year":"1990","unstructured":"Whitley D, Starkweather T, Bogart C (1990) Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Comput 14(3):347\u2013361","journal-title":"Parallel Comput"},{"issue":"11","key":"3922_CR11","doi-asserted-by":"publisher","first-page":"1542","DOI":"10.1287\/mnsc.40.11.1542","volume":"40","author":"B Malakooti","year":"1994","unstructured":"Malakooti B, Zhou YQ (1994) Feedforward artificial neural networks for solving discrete multiple criteria decision making problems. Manag Sci 40(11):1542\u20131561","journal-title":"Manag Sci"},{"issue":"2\u20133","key":"3922_CR12","doi-asserted-by":"crossref","first-page":"227","DOI":"10.3233\/FI-2014-1073","volume":"133","author":"S P\u0142aczek","year":"2014","unstructured":"P\u0142aczek S, Adhikari B (2014) Analysis of multilayer neural networks with direct and cross forward connection. Fundam Inf 133(2\u20133):227\u2013240","journal-title":"Fundam Inf"},{"key":"3922_CR13","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"C Bishop","year":"1995","unstructured":"Bishop C (1995) Neural networks for pattern recognition. Oxford University Press, Oxford"},{"key":"3922_CR14","volume-title":"Pattern recognition and neural networks","author":"BD Ripley","year":"2007","unstructured":"Ripley BD (2007) Pattern recognition and neural networks. Cambridge University Press, Cambridge"},{"key":"3922_CR15","unstructured":"Raiko T, Valpola H, LeCun Y (2012) Deep learning made easier by linear transformations in perceptrons. In: Artificial intelligence and statistics, pp 924\u2013932"},{"key":"3922_CR16","unstructured":"Schraudolph N (1998) Accelerated gradient descent by factor-centering decomposition. Technical report\/IDSIA 98"},{"key":"3922_CR17","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-642-35289-8_14","volume-title":"Neural networks: tricks of the trade","author":"NN Schraudolph","year":"2012","unstructured":"Schraudolph NN (2012) Centering neural network gradient factors. In: Montavon G, Orr GB, M\u00fcller KR (eds) Neural networks: tricks of the trade. Springer, Berlin, pp 205\u2013223"},{"key":"3922_CR18","doi-asserted-by":"crossref","unstructured":"Vatanen T, Raiko T, Valpola H, LeCun Y (2013) Pushing stochastic gradient towards second-order methods\u2014backpropagation learning with transformations in nonlinearities. In: International conference on neural information processing, Springer, pp 442\u2013449","DOI":"10.1007\/978-3-642-42054-2_55"},{"key":"3922_CR19","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. arXiv:1505.00387"},{"key":"3922_CR20","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in neural information processing systems, pp 2377\u20132385"},{"key":"3922_CR21","unstructured":"Huang G, Liu Z, Weinberger KQ (2016) Densely connected convolutional networks. arXiv:1608.06993"},{"key":"3922_CR22","unstructured":"Greff K, Srivastava RK, Schmidhuber J (2016) Highway and residual networks learn unrolled iterative estimation. arXiv:1612.07771"},{"key":"3922_CR23","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320\u20133328"},{"key":"3922_CR24","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1717\u20131724","DOI":"10.1109\/CVPR.2014.222"},{"key":"3922_CR25","unstructured":"Veit A, Wilber MJ, Belongie S (2016) Residual networks behave like ensembles of relatively shallow networks. In: Advances in neural information processing systems, pp 550\u2013558"},{"key":"3922_CR26","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1023\/A:1022648800760","volume":"5","author":"RE Schapire","year":"1990","unstructured":"Schapire RE (1990) The strength of weak learnability. Mach Learn 5:197\u2013227","journal-title":"Mach Learn"},{"issue":"3","key":"3922_CR27","doi-asserted-by":"publisher","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","volume":"2","author":"T Hastie","year":"2009","unstructured":"Hastie T, Rosset S, Zhu J, Zou H (2009) Multi-class adaboost. Stat Interface 2(3):349\u2013360","journal-title":"Stat Interface"},{"key":"3922_CR28","first-page":"437","volume":"14","author":"I Mukherjee","year":"2013","unstructured":"Mukherjee I, Schapire RE (2013) A theory of multiclass boosting. J Mach Learn Res 14:437\u2013497","journal-title":"J Mach Learn Res"},{"key":"3922_CR29","first-page":"933","volume":"4","author":"Y Freund","year":"2003","unstructured":"Freund Y, Iyer R, Schapire RE, Singer Y (2003) An efficient boosting algorithm for combining preferences. J Mach Learn Res 4:933\u2013969","journal-title":"J Mach Learn Res"},{"key":"3922_CR30","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv:1605.07146","DOI":"10.5244\/C.30.87"},{"key":"3922_CR31","unstructured":"Ba LJ, Caurana R (2014) Do deep nets really need to be deep? In: Advances in neural information processing systems, pp 2654\u20132662"},{"key":"3922_CR32","doi-asserted-by":"crossref","unstructured":"Bucilu C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp 535\u2013541","DOI":"10.1145\/1150402.1150464"},{"key":"3922_CR33","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"3922_CR34","unstructured":"Mosca A, Magoulas GD (2016) Regularizing deep learning ensembles by distillation. In: 6th international workshop on combinations of intelligent methods and applications (CIMA 2016), p 53"},{"key":"3922_CR35","unstructured":"Benenson R What is the class of this image? http:\/\/rodrigob.github.io\/are_we_there_yet\/build\/classification_datasets_results.html . Accessed 6 Dec 2018"},{"key":"3922_CR36","unstructured":"Lecun Y, Cortes C The MNIST database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/ . Accessed 6 Dec 2018"},{"key":"3922_CR37","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. vol 4, No. 4. Technical report, University of Toronto"},{"issue":"3","key":"3922_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252","journal-title":"Int J Comput Vis (IJCV)"},{"key":"3922_CR39","unstructured":"Wan L, Zeiler M, Zhang S, Cun YL, Fergus R (2013) Regularization of neural networks using dropconnect. In: Proceedings of the 30th international conference on machine learning (ICML-13), pp 1058\u20131066"},{"key":"3922_CR40","unstructured":"Graham B (2014) Fractional max-pooling. CoRR arXiv:1412.6071"},{"key":"3922_CR41","unstructured":"Clevert D, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). CoRR arXiv:1511.07289"},{"issue":"200","key":"3922_CR42","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","volume":"32","author":"M Friedman","year":"1937","unstructured":"Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32(200):675\u2013701","journal-title":"J Am Stat Assoc"},{"issue":"6","key":"3922_CR43","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon F (1945) Individual comparisons by ranking methods. Biometrics 1(6):80\u201383","journal-title":"Biometrics"},{"key":"3922_CR44","unstructured":"Mosca A, Magoulas GD (2017) Training convolutional networks with weight-wise adaptive learning rates. In: ESANN 2017 proceedings, European symposium on artificial neural networks, computational intelligence and machine learning. Bruges (Belgium), 26\u201328 April 2017, i6doc.com publ"},{"key":"3922_CR45","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"3922_CR46","unstructured":"Lu Y, Zhong A, Li Q, Dong B (2018) Beyond finite layer neural networks: bridging deep architectures and numerical differential equations. ICLR https:\/\/openreview.net\/forum?id=ryZ283gAZ . Accessed 6 Dec 2018"},{"key":"3922_CR47","unstructured":"Ciccone M, Gallieri M, Masci J, Osendorfer C, Gomez F (2018) NAIS-Net: stable deep networks from non-autonomous differential equations. CoRR arXiv:1804.07209"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3922-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-018-3922-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3922-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T11:08:09Z","timestamp":1775300889000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-018-3922-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"references-count":47,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["3922"],"URL":"https:\/\/doi.org\/10.1007\/s00521-018-3922-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"15 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors have received a hardware grant from NVIDIA for this research.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}