NV-BNN: An Accurate Deep Convolutional Neural Network Based on Binary STT-MRAM for Adaptive AI Edge

Binary STT-MRAM is a highly anticipated embedded non-volatile 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 STT-MRAM, we report the first binary deep convolutional neural net...

Full description

Saved in:
Bibliographic Details
Published in2019 56th ACM/IEEE Design Automation Conference (DAC) pp. 1 - 6
Main Authors Chang, Chih-Cheng, Wu, Ming-Hung, Lin, Jia-Wei, Li, Chun-Hsien, Parmar, Vivek, Lee, Heng-Yuan, Wei, Jeng-Hua, Sheu, Shyh-Shyuan, Suri, Manan, Chang, Tian-Sheuan, Hou, Tuo-Hung
Format Conference Proceeding
LanguageEnglish
Published ACM 01.06.2019
Subjects
Artificial intelligence
Computer architecture
Magnetic tunneling
Magnetization
Neural networks
Switches
Training
Online AccessGet full text

Cover

More Information
Summary:Binary STT-MRAM is a highly anticipated embedded non-volatile 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 STT-MRAM, 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 non-iterative training-with-noise and fine-tuning scheme.
DOI:10.1145/3316781.3317872