{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:24:27Z","timestamp":1782984267059,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Australian Research Council Projects","award":["FT-130101457"],"award-info":[{"award-number":["FT-130101457"]}]},{"name":"Australian Research Council Projects","award":["DP-140102164"],"award-info":[{"award-number":["DP-140102164"]}]},{"name":"Australian Research Council Projects","award":["LP-150100671"],"award-info":[{"award-number":["LP-150100671"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,5,1]]},"DOI":"10.1109\/tpami.2017.2701831","type":"journal-article","created":{"date-parts":[[2017,5,5]],"date-time":"2017-05-05T18:27:59Z","timestamp":1494008879000},"page":"1245-1258","source":"Crossref","is-referenced-by-count":46,"title":["Shakeout: A New Approach to Regularized Deep Neural Network Training"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-2025","authenticated-orcid":false,"given":"Guoliang","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref38","first-page":"3403","article-title":"On the inductive bias of dropout","volume":"16","author":"helmbold","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref33","first-page":"2523","article-title":"Improved dropout for shallow\n and deep learning","author":"li","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"3084","article-title":"Adaptive dropout for training deep neural networks","author":"ba","year":"2013","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref31","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00010-0"},{"key":"ref37","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Insights and applications","author":"gal","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref36","first-page":"2814","article-title":"Understanding dropout","author":"baldi","year":"2013","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref35","article-title":"An empirical analysis of dropout in\n piecewise linear networks","author":"warde-farley","year":"2013"},{"key":"ref34","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from\n overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref60","article-title":"Towards principled methods for training generative adversarial networks","volume":"2016","author":"arjovsky","year":"2017","journal-title":"Proc NIPS Workshop on Adversarial Training"},{"key":"ref62","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref61","article-title":"Wasserstein\n gan","author":"arjovsky","year":"2017"},{"key":"ref63","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref28","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref64","first-page":"2113","article-title":"Gradient-based hyperparameter optimization through reversible learning","author":"maclaurin","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref27","first-page":"1751","article-title":"Shakeout: A\n new regularized deep neural network training scheme","author":"kang","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref65","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref29","first-page":"950","article-title":"A simple weight decay can improve\n generalization","author":"moody","year":"1995","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref2","first-page":"4278","article-title":"Inception-v4,\n inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc Thirty-First AAAI Conf Artif Intell"},{"key":"ref1","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"0","journal-title":"Proc Europ Conf Comput Vis"},{"key":"ref20","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref22","article-title":"Deep compression:\n Compressing deep neural network with pruning, trained quantization and huffman coding","volume":"2","author":"han","year":"2015","journal-title":"CoRR abs\/1510 00149"},{"key":"ref21","first-page":"1135","article-title":"Learning both weights and connections for efficient\n neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref24","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref23","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"ref25","article-title":"Distilling\n the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref59","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref58","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"ref56","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref55","article-title":"Cuda-convnet","author":"krizhevsky","year":"2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.17"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2011.00771.x"},{"key":"ref52","article-title":"Learning Representations by Back-Propagating Errors","author":"williams","year":"1986","journal-title":"Nature"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref12","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in\n a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref13","article-title":"Improving neural networks by preventing co-adaptation of\n feature detectors","author":"hinton","year":"2012"},{"key":"ref14","first-page":"1097","article-title":"Imagenet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Wide residual networks","author":"zagoruyko","year":"0","journal-title":"Proc British Mach Vis Conf"},{"key":"ref16","first-page":"351","article-title":"Dropout\n training as adaptive regularization","author":"wager","year":"2013","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref17","first-page":"1752","article-title":"Dropout training for support vector\n machines","author":"chen","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref18","first-page":"410","article-title":"Learning with marginalized corrupted\n features","author":"van der maaten","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref19","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1989","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2476802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref7","article-title":"Deep learning\n with s-shaped rectified linear activation units","author":"jin","year":"2015"},{"key":"ref49","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref46","article-title":"Adding noise to the input of a model\n trained with a regularized objective","author":"rifai","year":"2011"},{"key":"ref45","first-page":"1091","article-title":"Sparse activity and sparse connectivity in supervised learning","volume":"14","author":"thom","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref48","first-page":"3590","article-title":"Robust\n dictionary learning with capped l1-norm","author":"jiang","year":"2015","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref44","article-title":"Spike-and-slab sparse coding for unsupervised feature discovery","author":"goodfellow","year":"2012"},{"key":"ref43","first-page":"1185","article-title":"Sparse\n feature learning for deep belief networks","author":"ranzato","year":"2008","journal-title":"Proc Adv Neural Inform Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8329157\/07920425.pdf?arnumber=7920425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T07:42:28Z","timestamp":1643182948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7920425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,1]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2701831","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,1]]}}}