Hardware implementation of RRAM based binarized neural networks
Resistive switching random access memory (RRAM) has been explored to accelerate the computation of neural networks. RRAM with linear conductance modulation is usually required for the efficient weight updating during the online training according to the back-propagation algorithm. However, most RRAM...
Main Authors: | Peng Huang, Zheng Zhou, Yizhou Zhang, Yachen Xiang, Runze Han, Lifeng Liu, Xiaoyan Liu, Jinfeng Kang |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2019-08-01
|
Series: | APL Materials |
Online Access: | http://dx.doi.org/10.1063/1.5116863 |
Similar Items
-
Flash Memory Array for Efficient Implementation of Deep Neural Networks
by: Runze Han, et al.
Published: (2021-05-01) -
A Self‐Terminated Operation Scheme for High‐Parallel and Energy‐Efficient Forming of RRAM Array
by: Yulin Feng, et al.
Published: (2020-04-01) -
Recovering accuracy of RRAM-based CIM for binarized neural network via Chip-in-the-loop training
by: Chong, Yi Sheng, et al.
Published: (2022) -
Negative Differential Resistance Effect in Ru-Based RRAM Device Fabricated by Atomic Layer Deposition
by: Yulin Feng, et al.
Published: (2019-03-01) -
Hardware Platform-Aware Binarized Neural Network Model Optimization
by: Quang Hieu Vo, et al.
Published: (2022-01-01)