{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T10:47:32Z","timestamp":1780656452685,"version":"3.54.1"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"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","doi-asserted-by":"publisher","award":["1815047"],"award-info":[{"award-number":["1815047"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005801","name":"Facebook","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005801","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2021,7,1]]},"DOI":"10.1109\/lca.2021.3108505","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T21:24:52Z","timestamp":1630358692000},"page":"126-129","source":"Crossref","is-referenced-by-count":3,"title":["SmaQ: Smart Quantization for DNN Training by Exploiting Value Clustering"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6846-8721","authenticated-orcid":false,"given":"Nima","family":"Shoghi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8664-5533","authenticated-orcid":false,"given":"Andrei","family":"Bersatti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moinuddin","family":"Qureshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6061-7825","authenticated-orcid":false,"given":"Hyesoon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0"},{"key":"ref10","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","article-title":"A study of BFLOAT16 for deep learning training","author":"kalamkar","year":"0"},{"key":"ref11","first-page":"7686","article-title":"Training deep neural networks with 8-bit floating point numbers","author":"wang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/0914050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_36"},{"key":"ref7","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0"},{"key":"ref2","article-title":"Shifted and squeezed 8-bit floating point format for low-precision training of deep neural networks","author":"cambier","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref1","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","author":"banner","year":"2018"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10208\/9479861\/9525237-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/9479861\/09525237.pdf?arnumber=9525237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:22Z","timestamp":1652194342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":11,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2021.3108505","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,1]]}}}