Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (2): 324-334.doi: 10.23919/JSEE.2023.000018

• ELECTRONICS TECHNOLOGY • Previous Articles    

Threshold-type memristor-based crossbar array design and its application in handwritten digit recognition

Qingjian LI, Yan LIANG(), Zhenzhou LU(), Guangyi WANG()   

  1. 1 School of Electronic and Information, Hangzhou Dianzi University, Hangzhou 310018, China
  • Received:2021-09-27 Online:2023-04-18 Published:2023-04-18
  • Contact: Yan LIANG E-mail:liangyan@hdu.edu.cn;luzhz@hdu.edu.cn;wanggyi@163.com
  • About author:
    LI Qingjian was born in 2000. He received his B.E. degree from Hangzhou Dianzi University, Hangzhou, China, in 2021. He is currently pursuing his M.S. degree at the University of Chinese Academy of Sciences. His research interests include nonlinear dynamics, memristive systems, and neural networks.E-mail: lqj@hdu.edu.cn

    LIANG Yan was born in 1988. She received her B.E. and Ph.D. degrees from the School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, China, in 2011 and 2017, respectively. She is an associate professor with Hangzhou Dianzi University. Her current research interests include memristive systems, nonlinear dynamics, and artificial neural network. E-mail: liangyan@hdu.edu.cn

    LU Zhenzhou was born in 1993. He received his B.E. and M.S. degrees from the School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, China, in 2011 and 2014, respectively. He is currently an engineer with Hangzhou Dianzi University. His current research interests include nonlinear dynamics, memristive systems, intrinsic safety, and wireless power transmission. E-mail: luzhz@hdu.edu.cn

    WANG Guangyi was born in 1957. He received his Ph.D. degree in electronic science and technology from the South China University of Technology, Guangzhou, China, in 2004. From 1996 to 2003, he was a professor with the Physics Department, Binzhou University. Since 2004, he has been a professor with the School of Electronic Information, Hangzhou Dianzi University. He is the author of two books, over 110 articles, with over 20 granted patents. His research interests include nonlinear dynamics, chaotic circuits, and memristive circuits. E-mail: wanggyi@163.com
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61801154;61771176), and the Zhejiang Provincial Natural Science Foundation of China (LY20F010008)

Abstract:

Neuromorphic computing simulates the operation of biological brain function for information processing and can potentially solve the bottleneck of the Von Neumann architecture. Inspired by the real characteristics of physical memristive devices, we propose a threshold-type nonlinear voltage-controlled memristor mathematical model which is used to design a novel memristor-based crossbar array. The presented crossbar array can simulate the synaptic weight in real number field rather than only positive number field. Theoretical analysis and simulation results of a 2×2 image inversion operation validate the feasibility of the proposed crossbar array and the necessary training and inference functions. Finally, the presented crossbar array is used to construct the neural network and then applied in the handwritten digit recognition. The Mixed National Institute of Standards and Technology (MNIST) database is adopted to train this neural network and it achieves a satisfactory accuracy.

Key words: memristor, threshold characteristic, modelling, electrical synapse, crossbar array