{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T11:43:13Z","timestamp":1725018193045},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"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":[[2022,1,17]]},"DOI":"10.1109\/asp-dac52403.2022.9712505","type":"proceedings-article","created":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T22:39:17Z","timestamp":1645483157000},"source":"Crossref","is-referenced-by-count":3,"title":["Toward Low-Bit Neural Network Training Accelerator by Dynamic Group Accumulation"],"prefix":"10.1109","author":[{"given":"Yixiong","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinshan","family":"Yue","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics of the Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","year":"0","journal-title":"NVDLA deep learning accelerator"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2946771"},{"key":"ref12","first-page":"7686","article-title":"Training deep neural networks with 8-bit floating point numbers","author":"wang","year":"0","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref13","first-page":"1","article-title":"A 40nm 4.81 TFLOPS\/W 8b Floating-Point Training Processor for Non-Sparse Neural Net works Using Shared Exponent Bias and 24-Way Fused Multiply-Add Tree","author":"park","year":"2021","journal-title":"2021 IEEE International Solid-State Circuits Con ference (ISSCC)"},{"key":"ref4","first-page":"33","article-title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","author":"zhuang","year":"0","journal-title":"Proceedings of the 34nd International Conference on Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662302"},{"key":"ref5","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","author":"evci","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218524"},{"key":"ref7","first-page":"144","article-title":"A 7nm 4-Core AI Chip with 25.6 TFLOPS Hybrid FP8 Training, 102.4 TOPS INT4 Inference and Workload-Aware Throttling","author":"agrawal","year":"0","journal-title":"2021 IEEE International Solid-State Circuits Conference-(ISSCC)"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classifi cation with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","author":"banner","year":"0","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"}],"event":{"name":"2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,1,17]]},"end":{"date-parts":[[2022,1,20]]}},"container-title":["2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9712466\/9712479\/09712505.pdf?arnumber=9712505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T21:08:33Z","timestamp":1655154513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,17]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/asp-dac52403.2022.9712505","relation":{},"subject":[],"published":{"date-parts":[[2022,1,17]]}}}