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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 56th Annual Design Automation Conference 2019, DAC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450367257
DOIs
StatePublished - 2 Jun 2019
Event56th Annual Design Automation Conference, DAC 2019 - Las Vegas, United States
Duration: 2 Jun 20196 Jun 2019

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

Conference

Conference56th Annual Design Automation Conference, DAC 2019
CountryUnited States
CityLas Vegas
Period2/06/196/06/19

Fingerprint Dive into the research topics of 'NV-BNN: An accurate deep convolutional neural network based on binary STT-MRAM for adaptive ai edge'. Together they form a unique fingerprint.

Cite this