{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:23:25Z","timestamp":1781281405158,"version":"3.54.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,25]]},"DOI":"10.1109\/iscas56072.2025.11044130","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:42:19Z","timestamp":1751046139000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["An Efficient Training Architecture for Nonlinear Softmax Function in Transformers"],"prefix":"10.1109","author":[{"given":"Haikuo","family":"Shao","sequence":"first","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2019","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref4","article-title":"Albert: A lite bert for self-supervised learning of language representations","volume":"abs\/1909.11942","author":"Lan","year":"2019","journal-title":"ArXiv"},{"issue":"8","key":"ref5","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","article-title":"Image transformer","volume-title":"ICML","author":"Parmar"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/764"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3145850"},{"key":"ref13","article-title":"Layer normalization","volume":"abs\/1607.06450","author":"Ba","year":"2016","journal-title":"ArXiv"},{"key":"ref14","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3317789"},{"key":"ref17","article-title":"Flexblock: A flexible dnn training accelerator with multi-mode block floating point support","volume":"abs\/2203.06673","author":"Noh","year":"2022","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3305569"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2016.7905501"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3120495"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3175534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.3002564"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181465"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref28","article-title":"Pointer sentinel mixture models","volume":"abs\/1609.07843","author":"Merity","year":"2016","journal-title":"ArXiv"},{"key":"ref29","article-title":"The goldilocks principle: Reading children\u2019s books with explicit memory representations","volume":"abs\/1511.02301","author":"Hill","year":"2015","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3665314.3670816"}],"event":{"name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"London, United Kingdom","start":{"date-parts":[[2025,5,25]]},"end":{"date-parts":[[2025,5,28]]}},"container-title":["2025 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11043142\/11042930\/11044130.pdf?arnumber=11044130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:46:45Z","timestamp":1751093205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,25]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iscas56072.2025.11044130","relation":{},"subject":[],"published":{"date-parts":[[2025,5,25]]}}}