NV-BNN: An accurate deep convolutional neural network based on binary STT-MRAM for adaptive ai edge

Chih Cheng Chang, Ming Hung Wu, Jia Wei Lin, Chun Hsien Li, Vivek Parmar, Heng Yuan Lee, Jeng Hua Wei, Shyh Shyuan Sheu, Manan Suri, Tian-Sheuan Chang, Tuo-Hung Hou

研究成果: Conference contribution同行評審

6 引文 斯高帕斯(Scopus)

摘要

Binary STT-MRAM is a highly anticipated embedded nonvolatile memory technology in advanced logic nodes < 28 nm. How to enable its in-memory computing (IMC) capability is critical for enhancing AI Edge. Based on the soon-available STTMRAM, we report the first binary deep convolutional neural network (NV-BNN) capable of both local and remote learning. Exploiting intrinsic cumulative switching probability, accurate online training of CIFAR-10 color images (∼ 90%) is realized using a relaxed endurance spec (switching ≤ 20 times) and hybrid digital/IMC design. For offline training, the accuracy loss due to imprecise weight placement can be mitigated using a rapid noniterative training-with-noise and fine-tuning scheme.

原文English
主出版物標題Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781450367257
DOIs
出版狀態Published - 2 六月 2019
事件56th Annual Design Automation Conference, DAC 2019 - Las Vegas, United States
持續時間: 2 六月 20196 六月 2019

出版系列

名字Proceedings - Design Automation Conference
ISSN(列印)0738-100X

Conference

Conference56th Annual Design Automation Conference, DAC 2019
國家/地區United States
城市Las Vegas
期間2/06/196/06/19

指紋

深入研究「NV-BNN: An accurate deep convolutional neural network based on binary STT-MRAM for adaptive ai edge」主題。共同形成了獨特的指紋。

引用此