{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:51:46Z","timestamp":1784199106393,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/tnnls.2020.2995884","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T21:14:26Z","timestamp":1591046066000},"page":"2030-2039","source":"Crossref","is-referenced-by-count":114,"title":["Probabilistic Knowledge Transfer for Lightweight Deep Representation Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5359-8315","authenticated-orcid":false,"given":"Maria","family":"Tzelepi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2803217"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456636"},{"key":"ref31","first-page":"3438","article-title":"Bayesian dark knowledge","author":"balan","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"Knowledge transfer pre-training","author":"tang","year":"2015","journal-title":"arXiv 1506 02256"},{"key":"ref37","article-title":"Improved knowledge distillation via teacher assistant","author":"mirzadeh","year":"2019","journal-title":"arXiv 1902 03393"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2722691"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref11","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","author":"chen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.11.022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2016.0110"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0788-3"},{"key":"ref17","first-page":"1310","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc 53rd Annu Allerton Conf Commun Control Comput (Allerton)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2597444"},{"key":"ref19","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"belkin","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790388"},{"key":"ref6","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref29","article-title":"Transferring knowledge from a RNN to a DNN","author":"chan","year":"2015","journal-title":"arXiv 1504 01483"},{"key":"ref5","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc Neural Inf Process Syst Deep Learn Workshop"},{"key":"ref7","first-page":"1","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472809"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851924"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557115"},{"key":"ref22","first-page":"1415","article-title":"Feature extraction by non-parametric mutual information maximization","volume":"3","author":"torkkola","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1946.0056"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00302"},{"key":"ref41","author":"turlach","year":"1993","journal-title":"Bandwidth Selection in Kernel Density Estimation A Review"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref25","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9420773\/09104915.pdf?arnumber=9104915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:16Z","timestamp":1652194396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9104915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":47,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2995884","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}