{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T16:35:24Z","timestamp":1764002124854,"version":"3.37.3"},"reference-count":18,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","funder":[{"name":"Key Project of the National Natural Science Foundation of China","award":["no. 61134009"],"award-info":[{"award-number":["no. 61134009"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61473077","61473078","61503075"],"award-info":[{"award-number":["61473077","61473078","61503075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Cooperative research funds of the National Natural Science Funds Overseas and Hong Kong and Macao scholars","award":["no. 61428302"],"award-info":[{"award-number":["no. 61428302"]}]},{"name":"Program for Changjiang Scholars from the Ministry of Education, and Innovation Program of Shanghai Municipal Education Commission","award":["no. 14ZZ067"],"award-info":[{"award-number":["no. 14ZZ067"]}]},{"name":"Shanghai Sailing Program","award":["no. 17YF1426100"],"award-info":[{"award-number":["no. 17YF1426100"]}]},{"name":"China Post-doctoral foundation","award":["no. 2016M601472"],"award-info":[{"award-number":["no. 2016M601472"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2018,3]]},"abstract":"<jats:p> Recently, deep learning has been widely applied in various areas and achieved remarkable research findings. The major reason that makes the deep learning paradigm successful is that it can effectively learn a hierarchical feature structure for the training data. However, most deep learning algorithms rely on massive well-labeled training datasets and hyper-parameter configurations. This paper proposed a novel methodology that uses the geometric characteristics of line-segment representations to optimize the hyper-parameters for the deep networks. The methodology is applied to a line-segment-based stacked auto-encoder to verify its effectiveness. It is found that the line-segment-based visualizations can increase the interpretability of the deep models and facilitate the configurations for the hyper-parameters. <\/jats:p>","DOI":"10.1142\/s0218001418510023","type":"journal-article","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T03:21:15Z","timestamp":1498188075000},"page":"1851002","source":"Crossref","is-referenced-by-count":7,"title":["A Novel Method Based on Line-Segment Visualizations for Hyper-Parameter Optimization in Deep Networks"],"prefix":"10.1142","volume":"32","author":[{"given":"Xue-song","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Information Science, Donghua University, Shanghai 201620, P. R. China"}]},{"given":"Yongsheng","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Information Science, Donghua University, Shanghai 201620, P. R. China"}]},{"given":"Kuangrong","family":"Hao","sequence":"additional","affiliation":[{"name":"Department of Information Science, Donghua University, Shanghai 201620, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2017,11,22]]},"reference":[{"key":"S0218001418510023BIB002","first-page":"115","volume":"1","author":"Bergstra J.","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"S0218001418510023BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2469673"},{"key":"S0218001418510023BIB005","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"S0218001418510023BIB006","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2479223"},{"key":"S0218001418510023BIB007","first-page":"281","volume":"13","author":"James B.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"S0218001418510023BIB008","first-page":"512","volume":"33","author":"Kivinen J.","year":"2014","journal-title":"AISTATS"},{"key":"S0218001418510023BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/34.879802"},{"key":"S0218001418510023BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2008.2007988"},{"key":"S0218001418510023BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2004.832820"},{"key":"S0218001418510023BIB012","first-page":"818","volume":"8689","author":"Matthew D. Z.","year":"2013","journal-title":"ECCV"},{"key":"S0218001418510023BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/34.481545"},{"key":"S0218001418510023BIB015","first-page":"1185","volume":"20","author":"Ranzato M.","year":"2007","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001418510023BIB016","first-page":"833","volume":"2011","author":"Rifai S.","year":"2011","journal-title":"ICML"},{"key":"S0218001418510023BIB019","first-page":"1","volume":"44","author":"Tomczak J. M.","year":"2015","journal-title":"Neural Process. Lett."},{"key":"S0218001418510023BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.300"},{"key":"S0218001418510023BIB022","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.10.031"},{"key":"S0218001418510023BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2376939"},{"key":"S0218001418510023BIB024","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.020"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001418510023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T15:22:31Z","timestamp":1565104951000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001418510023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,22]]},"references-count":18,"journal-issue":{"issue":"03","published-online":{"date-parts":[[2017,11,22]]},"published-print":{"date-parts":[[2018,3]]}},"alternative-id":["10.1142\/S0218001418510023"],"URL":"https:\/\/doi.org\/10.1142\/s0218001418510023","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2017,11,22]]}}}