Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/159293
Title: Hardware-friendly stochastic and adaptive learning in memristor convolutional neural networks
Authors: Zhang, Wei
Pan, Lunshuai
Yan, Xuelong
Zhao, Guangchao
Chen, Hong
Wang, Xingli
Tay, Beng Kang
Zhong, Gaokuo
Li, Jiangyu
Huang, Mingqiang
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Source: Zhang, W., Pan, L., Yan, X., Zhao, G., Chen, H., Wang, X., Tay, B. K., Zhong, G., Li, J. & Huang, M. (2021). Hardware-friendly stochastic and adaptive learning in memristor convolutional neural networks. Advanced Intelligent Systems, 3(9), 2100041-. https://dx.doi.org/10.1002/aisy.202100041
Journal: Advanced Intelligent Systems
Abstract: Memristors offer great advantages as a new hardware solution for neuromorphic computing due to their fast and energy-efficient matrix vector multiplication. However, the nonlinear weight updating property of memristors makes it difficult to be trained in a neural network learning process. Several compensation schemes have been proposed to mitigate the updating error caused by nonlinearity; nevertheless, they usually involve complex peripheral circuits design. Herein, stochastic and adaptive learning methods for weight updating are developed, in which the inaccuracy caused by the memristor nonlinearity can be effectively suppressed. In addition, compared with the traditional nonlinear stochastic gradient descent (SGD) updating algorithm or the piecewise linear (PL) method, which are most often used in memristor neural network, the design is more hardware friendly and energy efficient without the consideration of pulse numbers, duration, and directions. Effectiveness of the proposed method is investigated on the training of LeNet-5 convolutional neural network. High accuracy, about 93.88%, on the Modified National Institute of Standards and Technology handwriting digits datasets is achieved (with typical memristor nonlinearity as ±1), which is close to the network with complex PL method (94.7%) and is higher than the original nonlinear SGD method (90.14%).
URI: https://hdl.handle.net/10356/159293
ISSN: 2640-4567
DOI: 10.1002/aisy.202100041
Schools: School of Electrical and Electronic Engineering 
Research Centres: CNRS International NTU THALES Research Alliances 
Rights: © 2021 The Authors. Advanced Intelligent Systems published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Web of ScienceTM
Citations 20

12
Updated on Oct 25, 2023

Page view(s)

116
Updated on Jun 18, 2024

Download(s) 50

48
Updated on Jun 18, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.