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

CC Chang, MH Wu, JW Lin, CH Li, V Parmar… - Proceedings of the 56th …, 2019 - dl.acm.org
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 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 …

[引用][C] Nv-bnn: An accurate deep convolutional neural network based on binary stt-mram for adaptive ai edge. In 2019 56th ACM/IEEE Design Automation Conference …

CC Chang, MH Wu, JW Lin, CH Li, V Parmar, HY Lee… - 2019 - IEEE
以上显示的是最相近的搜索结果。 查看全部搜索结果