{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:59:24Z","timestamp":1757591964149,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/1000000010","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1901378,CCF-1919117,CCF-1937500"],"award-info":[{"award-number":["CCF-1901378,CCF-1919117,CCF-1937500"]}],"id":[{"id":"10.13039\/1000000010","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.23919\/date56975.2023.10137222","type":"proceedings-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T19:32:57Z","timestamp":1685734377000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["ESRU: Extremely Low-Bit and Hardware-Efficient Stochastic Rounding Unit Design for Low-Bit DNN Training"],"prefix":"10.23919","author":[{"given":"Sung-En","family":"Chang","sequence":"first","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Lu","sequence":"additional","affiliation":[{"name":"Simon Fraser University,Burnaby,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengshu","family":"Sun","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyu","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Ma","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengang","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyue","family":"Xie","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghai","family":"Qin","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenman","family":"Fang","sequence":"additional","affiliation":[{"name":"Simon Fraser University,Burnaby,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TIT.2011.2164234"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.48550\/arXiv.1802.02611"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref4","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref6","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Intl. conf. on machine learning","author":"Gupta","year":"2015"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/0925-2312(92)90014-G"},{"year":"2019","journal-title":"IEEE Std 754\u20132019 (Revision of IEEE 754\u20132008)","article-title":"IEEE. Ieee standard for floating-point arithmetic","key":"ref9"},{"key":"ref10","article-title":"Digital systems design using VHDL","author":"Roth","year":"2016","journal-title":"Cengage Learning"},{"key":"ref11","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"NIPS"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1088\/1674-4926\/41\/2\/022403"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/IJCNN52387.2021.9533756"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/IJCNN.2017.7966324"},{"key":"ref15","article-title":"Low-precision floating-point schemes for neural network training","author":"Ortiz","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Low-precision floating-point schemes for neural network training","volume":"abs\/1804.05267","author":"Ortiz","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref18","article-title":"Training deep neural networks with 8-bit floating point numbers","volume":"31","author":"Wang","year":"2018","journal-title":"NIPS"},{"key":"ref19","article-title":"Huggingfaces transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Training and inference with integers in deep neural networks","author":"Wu","year":"2018","journal-title":"arXiv preprint"},{"volume-title":"Xilinx. Vitis unified software platform","year":"2021","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1016\/j.neunet.2019.12.027"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1609\/aaai.v35i4.16462"},{"key":"ref24","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR42600.2020.00204"}],"event":{"name":"2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)","start":{"date-parts":[[2023,4,17]]},"location":"Antwerp, Belgium","end":{"date-parts":[[2023,4,19]]}},"container-title":["2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10136870\/10136706\/10137222.pdf?arnumber=10137222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T06:24:59Z","timestamp":1709274299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10137222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/date56975.2023.10137222","relation":{},"subject":[],"published":{"date-parts":[[2023,4]]}}}