{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T18:53:59Z","timestamp":1775933639201,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003393","name":"Digital Annealer (DA) of Fujitsu Laboratories Ltd.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003393","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003393","name":"Fujitsu Consulting (Canada) Inc.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003393","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tnnls.2021.3069970","type":"journal-article","created":{"date-parts":[[2021,4,8]],"date-time":"2021-04-08T21:29:41Z","timestamp":1617917381000},"page":"5279-5292","source":"Crossref","is-referenced-by-count":39,"title":["EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9636-863X","authenticated-orcid":false,"given":"Hojjat","family":"Salehinejad","sequence":"first","affiliation":[{"name":"Department of Electrical &#x0026; Computer Engineering, University of Toronto, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6254-1660","authenticated-orcid":false,"given":"Shahrokh","family":"Valaee","sequence":"additional","affiliation":[{"name":"Department of Electrical &#x0026; Computer Engineering, University of Toronto, Toronto, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"issue":"1","key":"ref2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/b18401"},{"key":"ref4","first-page":"3084","article-title":"Adaptive dropout for training deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref5","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11634"},{"key":"ref7","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"key":"ref8","article-title":"Survey of dropout methods for deep neural networks","author":"Labach","year":"2019","journal-title":"arXiv:1904.13310"},{"key":"ref9","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref10","article-title":"Rethinking the value of network pruning","author":"Liu","year":"2018","journal-title":"arXiv:1810.05270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.4.473"},{"key":"ref12","article-title":"Soft weight-sharing for neural network compression","author":"Ullrich","year":"2017","journal-title":"arXiv:1702.04008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682914"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-61566-0_39"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969121"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414645"},{"key":"ref17","first-page":"1","article-title":"A tutorial on energy-based learning","volume":"1","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30504-7_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.09.042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"ref21","article-title":"Your classifier is secretly an energy based model and you should treat it like one","author":"Grathwohl","year":"2019","journal-title":"arXiv:1912.03263"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322333"},{"key":"ref23","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv:1503.02531"},{"key":"ref24","article-title":"Dealing with a large number of classes\u2013likelihood, discrimination or ranking?","author":"Barber","year":"2016","journal-title":"arXiv:1606.06959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008923215028"},{"key":"ref26","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"arXiv:1310.4546"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2014.7136466"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2014.6900322"},{"key":"ref29","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"ref30","first-page":"76","article-title":"On stagnation of the differential evolution algorithm","volume-title":"Proc. MENDEL","author":"Lampinen"},{"key":"ref31","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref32","article-title":"Deep learning for classical Japanese literature","author":"Clanuwat","year":"2018","journal-title":"arXiv:1812.01718"},{"key":"ref33","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref38","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5MB model size","author":"Iandola","year":"2016","journal-title":"arXiv:1602.07360"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","article-title":"Pruning filters for efficient ConvNets","author":"Li","year":"2016","journal-title":"arXiv:1608.08710"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975796"},{"key":"ref43","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref44","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref45","article-title":"AENet: Learning deep audio features for video analysis","author":"Takahashi","year":"2017","journal-title":"arXiv:1701.00599"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9911935\/09399169.pdf?arnumber=9399169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:04:06Z","timestamp":1704841446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9399169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3069970","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}