{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T10:51:23Z","timestamp":1760784683107,"version":"3.37.3"},"reference-count":25,"publisher":"Wiley","license":[{"start":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T00:00:00Z","timestamp":1558310400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["19YJAZH076","2018KRM065"],"award-info":[{"award-number":["19YJAZH076","2018KRM065"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Soft Science Research Program","award":["19YJAZH076","2018KRM065"],"award-info":[{"award-number":["19YJAZH076","2018KRM065"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2019,5,20]]},"abstract":"<jats:p>In this paper, we propose a novel multitask learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multitask learning problem, we propose to learn a low-rank deep network so that the relation among different tasks can be explored. We proposed to minimize the number of independent parameter rows of one fully connected layer to explore the relations among different tasks, which is measured by the nuclear norm of the parameter of one fully connected layer, and seek a low-rank parameter matrix. Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty so that the useful features learned by the lower layers can be selected. The learning problem is solved by an iterative algorithm based on gradient descent and back-propagation algorithms. The proposed algorithm is evaluated over benchmark datasets of multiple face attribute prediction, multitask natural language processing, and joint economics index predictions. The evaluation results show the advantage of the low-rank deep CNN model over multitask problems.<\/jats:p>","DOI":"10.1155\/2019\/7410701","type":"journal-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T19:31:07Z","timestamp":1558380667000},"page":"1-10","source":"Crossref","is-referenced-by-count":9,"title":["Low-Rank Deep Convolutional Neural Network for Multitask Learning"],"prefix":"10.1155","volume":"2019","author":[{"given":"Fang","family":"Su","sequence":"first","affiliation":[{"name":"Shaanxi University of Science & Technology, Xi\u2019an, Shaanxi Province 710021, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4795-5520","authenticated-orcid":true,"given":"Hai-Yang","family":"Shang","sequence":"additional","affiliation":[{"name":"Northwest University of Political Science and Law, Xi\u2019an, Shaanxi Province 710063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9582-4966","authenticated-orcid":true,"given":"Jing-Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"first-page":"41","volume-title":"Multi-task feature learning","year":"2007","key":"1"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1023\/a:1007379606734"},{"first-page":"745","volume-title":"Clustered multi-task learning: a convex formulation","year":"2009","key":"5"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1234-5"},{"key":"8","first-page":"35","volume":"8","year":"2007","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Neural Computing and Applications","first-page":"1","year":"2018","key":"9"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-007-0108-8"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1080\/0952813x.2014.886300"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-008-0225-z"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1080\/0952813x.2017.1409286"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1080\/09528139208953735"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1080\/0952813x.2018.1467495"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1007\/bf01424225"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-015-2069-7"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.01.008"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7186762"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8141259"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349"},{"journal-title":"Neural Computing and Applications","first-page":"1","year":"2017","key":"30"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68935-7_1"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-95957-3_15"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2688363"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/7410701.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/7410701.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/7410701.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T19:31:10Z","timestamp":1558380670000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cin\/2019\/7410701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,20]]},"references-count":25,"alternative-id":["7410701","7410701"],"URL":"https:\/\/doi.org\/10.1155\/2019\/7410701","relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2019,5,20]]}}}