{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:26:39Z","timestamp":1777994799421,"version":"3.51.4"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF) through the Real-Time Machine Learning Program","doi-asserted-by":"publisher","award":["1937592"],"award-info":[{"award-number":["1937592"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF) through the Real-Time Machine Learning Program","doi-asserted-by":"publisher","award":["2053279"],"award-info":[{"award-number":["2053279"]}],"id":[{"id":"10.13039\/100000001","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":[[2023,10]]},"DOI":"10.1109\/tnnls.2021.3138056","type":"journal-article","created":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T15:29:34Z","timestamp":1646234974000},"page":"7099-7113","source":"Crossref","is-referenced-by-count":2,"title":["SmartDeal: Remodeling Deep Network Weights for Efficient Inference and Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0360-0402","authenticated-orcid":false,"given":"Xiaohan","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5889-0729","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2873-2153","authenticated-orcid":false,"given":"Haoran","family":"You","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaojian","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonggan","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2050-5693","authenticated-orcid":false,"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"442","article-title":"Tensorizing neural networks","author":"novikov","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref56","article-title":"The lottery tickets hypothesis for supervised and self-supervised pre-training in computer vision models","author":"chen","year":"2020","journal-title":"arXiv 2012 06908"},{"key":"ref15","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"arXiv 1606 06160 [cs]"},{"key":"ref59","year":"2019","journal-title":"AVNET Ultra96"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2017.2732698"},{"key":"ref58","year":"2020","journal-title":"Micronet Challenge"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref11","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"arXiv 1905 11946"},{"key":"ref55","article-title":"The lottery ticket hypothesis for pre-trained BERT networks","author":"chen","year":"2020","journal-title":"arXiv 2007 12223"},{"key":"ref10","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref17","article-title":"ShiftAddNet: A hardware-inspired deep network","author":"you","year":"2020","journal-title":"arXiv 2010 12785"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref18","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref46","article-title":"SWALP: Stochastic weight averaging in low-precision training","author":"yang","year":"2019","journal-title":"arXiv 1904 11943"},{"key":"ref45","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"arXiv 1803 05407"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"ref47","first-page":"7531","article-title":"Latent weights do not exist: Rethinking binarized neural network optimization","author":"helwegen","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080215"},{"key":"ref43","article-title":"Exploring the regularity of sparse structure in convolutional neural networks","author":"mao","year":"2017","journal-title":"arXiv 1705 08922"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304041"},{"key":"ref8","article-title":"SignSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018","journal-title":"arXiv 1802 04434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662447"},{"key":"ref4","first-page":"5139","article-title":"E2-train: Training state-of-the-art CNNs with over 80% less energy","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_29"},{"key":"ref5","article-title":"Drawing early-bird tickets: Towards more efficient training of deep networks","author":"you","year":"2019","journal-title":"arXiv 1909 11957"},{"key":"ref40","article-title":"Deep k-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions","author":"wu","year":"2018","journal-title":"arXiv 1806 09228"},{"key":"ref35","article-title":"Degree-quant: Quantization-aware training for graph neural networks","author":"tailor","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref36","first-page":"12127","article-title":"Fractrain: Fractionally squeezing bit savings both temporally and spatially for efficient dnn training","volume":"33","author":"fu","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_4"},{"key":"ref75","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref30","author":"gui","year":"2019","journal-title":"Adversarially trained model compression When robustness meets efficiency"},{"key":"ref74","year":"2019","journal-title":"Primetime px Signoff power analysis"},{"key":"ref33","article-title":"Mixed precision quantization of ConvNets via differentiable neural architecture search","author":"wu","year":"2018","journal-title":"arXiv 1812 00090"},{"key":"ref32","article-title":"Mixed precision training","author":"micikevicius","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00082"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541967"},{"key":"ref39","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"arXiv 1412 6115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref71","year":"2019","journal-title":"NVIDIA Jetson TX2 Delivers Twicethe Intelligence to the Edge"},{"key":"ref70","article-title":"Interstellar: Using Halide’s scheduling language to analyze DNN accelerators","author":"yang","year":"2018","journal-title":"arXiv 1809 04070"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"ref72","year":"2019","journal-title":"NVIDIA Tesla V100 Tensor Core GPU"},{"key":"ref24","article-title":"Triple wins: Boosting accuracy, robustness and efficiency together by enabling input-adaptive inference","author":"hu","year":"2020","journal-title":"arXiv 2002 10025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref20","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.027"},{"key":"ref63","first-page":"7675","article-title":"Training deep neural networks with 8-bit floating point numbers","author":"wang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref66","article-title":"Learned step size quantization","author":"esser","year":"2019","journal-title":"arXiv 1902 08153"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8010078"},{"key":"ref28","article-title":"Model compression via distillation and quantization","author":"polino","year":"2018","journal-title":"arXiv 1802 05668"},{"key":"ref27","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"mishra","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref29","article-title":"Graph-adaptive pruning for efficient inference of convolutional neural networks","author":"wang","year":"2018","journal-title":"arXiv 1811 08589"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref62","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","author":"banner","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10273172\/9724645-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09724645.pdf?arnumber=9724645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:56:05Z","timestamp":1769493365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9724645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":75,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3138056","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}