{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:54:24Z","timestamp":1775598864464,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"School of Computer Science and Engineering, UNSW Sydney, Tuition Fee Scholarship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tcad.2023.3253045","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T18:42:19Z","timestamp":1678128139000},"page":"3505-3518","source":"Crossref","is-referenced-by-count":21,"title":["ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5820-8985","authenticated-orcid":false,"given":"Jing","family":"Gong","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, UNSW Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3691-4130","authenticated-orcid":false,"given":"Hassaan","family":"Saadat","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Telecommunications, UNSW Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9034-9905","authenticated-orcid":false,"given":"Hasindu","family":"Gamaarachchi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, UNSW Sydney, Sydney, NSW, Australia"}]},{"given":"Haris","family":"Javaid","sequence":"additional","affiliation":[{"name":"Adaptive, Embedded and AI Group, AMD, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6636-9738","authenticated-orcid":false,"given":"Xiaobo Sharon","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiaobo Sharon Hu with the Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"}]},{"given":"Sri","family":"Parameswaran","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref13","year":"2022","journal-title":"NVIDIA TENSOR CORES unprecedented acceleration for HPC and AI"},{"key":"ref35","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref12","author":"wang","year":"2019","journal-title":"Bfloat16 The secret to high performance on cloud tpus"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","author":"vishwanath","year":"2019","journal-title":"Video series Mixed-precision training techniques using tensor cores for deep learning"},{"key":"ref14","author":"cueva","year":"2020","journal-title":"Intel® deep learning boost new deep learning instruction bfloat16"},{"key":"ref36","author":"mrazek","year":"2020","journal-title":"TFapprox"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"Mixed precision training","author":"micikevicius","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref10","article-title":"Neural gradients are near-lognormal: Improved quantized and sparse training","author":"chmiel","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","first-page":"529","article-title":"When and why are pre-trained word embeddings useful for neural machine translation","author":"ye","year":"2018","journal-title":"Proc HLT-NAACL"},{"key":"ref2","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","author":"cai","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013541"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.3030663"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2893356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2018.2792902"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2880742"},{"key":"ref24","article-title":"Design and optimization of approximate multipliers and dividers for integer and floating-point arithmetic","author":"saadat","year":"2021"},{"key":"ref23","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 (ICLR)"},{"key":"ref26","article-title":"High performance convolutional neural networks for document processing","author":"chellapilla","year":"2006","journal-title":"Proc Int'l Workshop Frontiers in Handwriting Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1962.5219391"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO49542.2019.8961780"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref27","author":"chetlur","year":"2014","journal-title":"cuDNN Efficient Primitives for Deep Learning"},{"key":"ref29","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116315"},{"key":"ref9","author":"gong","year":"2022","journal-title":"APPROX"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196012"},{"key":"ref6","year":"2019","journal-title":"Deep learning frameworks"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116299"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10288105\/10059158.pdf?arnumber=10059158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T19:03:08Z","timestamp":1699470188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10059158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":36,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2023.3253045","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}