{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:56:36Z","timestamp":1753887396232,"version":"3.41.2"},"reference-count":30,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2019,3,10]],"date-time":"2019-03-10T00:00:00Z","timestamp":1552176000000},"content-version":"vor","delay-in-days":68,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61501230","61732006","61876082","61861130366"],"award-info":[{"award-number":["61501230","61732006","61876082","61861130366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2019,1]]},"abstract":"<jats:p>In recent years, self\u2010paced learning (SPL) has attracted much attention due to its improvement to nonconvex optimization based machine learning algorithms. As a methodology introduced from human learning, SPL dynamically evaluates the learning difficulty of each sample and provides the weighted learning model against the negative effects from hard\u2010learning samples. In this study, we proposed a cognitive driven SPL method, i.e., retrospective robust self\u2010paced learning (R2SPL), which is inspired by the following two issues in human learning process: the misclassified samples are more impressive in upcoming learning, and the model of the follow\u2010up learning process based on large number of samples can be used to reduce the risk of poor generalization in initial learning phase. We simultaneously estimated the degrees of learning\u2010difficulty and misclassified in each step of SPL and proposed a framework to construct multilevel SPL for improving the robustness of the initial learning phase of SPL. The proposed method can be viewed as a multilayer model and the output of the previous layer can guide constructing robust initialization model of the next layer. The experimental results show that the R2SPL outperforms the conventional self\u2010paced learning models in classification task.<\/jats:p>","DOI":"10.1155\/2019\/8127869","type":"journal-article","created":{"date-parts":[[2019,3,10]],"date-time":"2019-03-10T23:31:21Z","timestamp":1552260681000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cognitive Driven Multilayer Self\u2010Paced Learning with Misclassified Samples"],"prefix":"10.1155","volume":"2019","author":[{"given":"Qi","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Ning","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7879-7625","authenticated-orcid":false,"given":"Donghai","family":"Guan","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2019,3,10]]},"reference":[{"key":"e_1_2_9_1_2","unstructured":"BengioY. LouradourJ. CollobertR. andWestonJ. Curriculum learning Proceedings of the 26th International Conference On Machine Learning ICML 2009 June 2009 Canada 41\u201348 2-s2.0-71149116544."},{"key":"e_1_2_9_2_2","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"Kumar M. P.","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"JiangL. MengD. ZhaoQ. ShanS. andHauptmannA. G. Self-paced curriculum learning 2 Proceedings of the AAAI 2015.","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"e_1_2_9_4_2","unstructured":"ZhaoQ. MengD. JiangL. XieQ. XuZ. andHauptmannA. G. Self-paced learning for Matrix factorization Proceedings of the 29th AAAI Conference on Artificial Intelligence AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference IAAI 2015 2015 3196\u20133202 2-s2.0-84960086094."},{"key":"e_1_2_9_5_2","doi-asserted-by":"crossref","unstructured":"SupancicIIIJ. S.andRamananD. Self-paced learning for long-term tracking Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 June 2013 2379\u20132386 2-s2.0-84887368146.","DOI":"10.1109\/CVPR.2013.308"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1874-1029(13)60052-X"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2007.07.001"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.08.002"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2307881"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2009.191"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2430359"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2005.05.019"},{"key":"e_1_2_9_14_2","unstructured":"JiangL. MengD. MitamuraT. andHauptmannA. G. Easy samples first: Self-paced reranking for zero-example multimedia search Proceedings of the 2014 ACM Conference on Multimedia MM 2014 November 2014 USA 547\u2013556 2-s2.0-84913585680."},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.005"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"FanY. HeR. LiangJ. andHuB.-G. Self-paced learning: an implicit regularization perspective 3 Proceedings of the AAAI 2017.","DOI":"10.1609\/aaai.v31i1.10809"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.4310\/SII.2009.v2.n3.a8"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"LvF.andNevatiaR. Recognition and segmentation of 3-d human action using hmm and multi-class adaboost Proceedings of the European Conference on Computer Vision 2006 Springer 359\u2013372.","DOI":"10.1007\/11744085_28"},{"key":"e_1_2_9_19_2","first-page":"1311","article-title":"Fast and robust classification using asymmetric adaboost and a detector cascade","author":"Viola P.","year":"2002","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007618119488"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2021941"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2652459"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1162\/153244302760185243"},{"key":"e_1_2_9_24_2","unstructured":"SchohnG.andCohnD. Less is more: Active learning with support vector machines Proceedings of the ICML 2000 Citeseer 839\u2013846."},{"key":"e_1_2_9_25_2","unstructured":"TongS.andChangE. Support vector machine active learning for image retrieval Proceedings of the 9th ACM International Conference on Multimedia October 2001 107\u2013118 2-s2.0-0034792634."},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2004.03.004"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(88)90014-X"},{"key":"e_1_2_9_28_2","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"Taylor M. E.","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2016.2528162"},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"VinyalsO. ToshevA. BengioS. andErhanD. Show and tell: A neural image caption generator Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR 2015 June 2015 3156\u20133164 2-s2.0-84946747440.","DOI":"10.1109\/CVPR.2015.7298935"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2019\/8127869.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2019\/8127869.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2019\/8127869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T14:37:11Z","timestamp":1723041431000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2019\/8127869"}},"subtitle":[],"editor":[{"given":"Ke","family":"Deng","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["10.1155\/2019\/8127869"],"URL":"https:\/\/doi.org\/10.1155\/2019\/8127869","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2019,1]]},"assertion":[{"value":"2018-11-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8127869"}}