What is the impact of discrete memristor on the performance of neural network: A research on discrete memristor-based BP neural network.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

Artificial neural networks are receiving increasing attention from researchers. However, with the advent of big data era, artificial neural networks are limited by the Von Neumann architecture, making it difficult to make new breakthroughs in hardware implementation. Discrete-time memristor, emerging as a research focus in recent years, are anticipated to address this challenge effectively. To enrich the theoretical research of memristors in artificial neural networks, this paper studies BP neural networks based on various discrete memristors. Firstly, the concept of discrete memristor and several classical discrete memristor models are introduced. Based on these models, the discrete memristor-based BP neural networks are designed. Finally, these networks are utilized for achieving handwritten digit classification and speech feature classification, respectively. The results show that linear discrete memristors perform better than nonlinear discrete memristors, and a simple linear discrete memristor-based BP neural network has the best performance, reaching 97.40% (handwritten digit classification) and 93.78% (speech feature classification), respectively. In addition, some fundamental issues are also discussed, such as the effects of linear, nonlinear memristors, and initial charges on the performance of neural networks.

Authors

  • Yuexi Peng
    School of Computer Science, Xiangtan University, Xiangtan 411105, PR China; College of Computer Science and Engineering, Jishou University, Jishou 416000, PR China. Electronic address: yuexipeng@xtu.edu.cn.
  • Maolin Li
    The National Centre for Text Mining, School of Computer Science, University of Manchester, Road, M13 9PL, Oxford, UK.
  • Zhijun Li
  • Minglin Ma
    School of Automation and Electronic Information, Xiangtan University, Xiangtan 411105, PR China.
  • Mengjiao Wang
    Greenpeace Research Laboratories, Innovation Centre Phase 2, University of Exeter, Exeter, United Kingdom.
  • Shaobo He
    School of Automation and Electronic Information, Xiangtan University, Xiangtan, 411105, China. Electronic address: heshaobo_123@163.com.