{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:48:49Z","timestamp":1781884129525,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2996936","type":"journal-article","created":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T20:32:50Z","timestamp":1590179570000},"page":"96963-96974","source":"Crossref","is-referenced-by-count":23,"title":["Learning Sparse Low-Precision Neural Networks With Learnable Regularization"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4496-0738","authenticated-orcid":false,"given":"Yoojin","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9421-6037","authenticated-orcid":false,"given":"Mostafa","family":"El-Khamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungwon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"1","article-title":"Soft weight-sharing for neural network compression","author":"ullrich","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","first-page":"2178","article-title":"Runtime neural pruning","author":"lin","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","author":"guo","year":"2016","journal-title":"Proc Adv in Neural Inf Process Syst"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"ref37","first-page":"1","article-title":"Towards the limit of network quantization","author":"choi","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref36","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref34","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref60","first-page":"711","article-title":"On single image scale-up using sparse-representations","author":"zeyde","year":"2010","journal-title":"Proc Int Conf Curves Surf"},{"key":"ref28","first-page":"1","article-title":"Relaxed quantization for discretized neural networks","author":"louizos","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178146"},{"key":"ref29","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"13","article-title":"Stochastic approximations and perturbations in forward-backward splitting for monotone operators","volume":"1","author":"combettes","year":"2016","journal-title":"Pure Appl Funct Anal"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref21","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018","journal-title":"arXiv 1805 06085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"key":"ref50","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013","journal-title":"arXiv 1308 3432"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref56","author":"seward","year":"1998","journal-title":"bzip2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00160"},{"key":"ref10","first-page":"1","article-title":"Trained ternary quantization","author":"zhu","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref40","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","author":"agustsson","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"1","article-title":"Loss-aware binarization of deep networks","author":"hou","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref13","first-page":"1","article-title":"Loss-aware weight quantization of deep networks","author":"hou","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00982"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/18M1166134"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24033\/bsmf.1625"},{"key":"ref18","author":"yosida","year":"1965","journal-title":"Functional Analysis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s40687-018-0177-6"},{"key":"ref4","author":"cover","year":"2012","journal-title":"Elements of Information Theory"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref6","first-page":"1","article-title":"Neural networks with few multiplications","author":"lin","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref7","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref9","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":"ref46","first-page":"10","article-title":"1.1 computing’s energy problem (and what we can do about it)","author":"horowitz","year":"2014","journal-title":"IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.4.473"},{"key":"ref47","volume":"159","author":"gersho","year":"2012","journal-title":"Vector Quantization and Signal Compression"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2886192"},{"key":"ref41","first-page":"3290","article-title":"Bayesian compression for deep learning","author":"louizos","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2975903"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09098870.pdf?arnumber=9098870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:15Z","timestamp":1639770735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9098870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2996936","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}