Analog-circuit implementation of multiplicative spike-timing-dependent plasticity with linear decay

• Moriya Satoshi

  Research Institute of Electrical Communication, Tohoku University

• Kato Tatsuki

  Research Institute of Electrical Communication, Tohoku University

• Oguchi Daisuke

  Research Institute of Electrical Communication, Tohoku University

• Yamamoto Hideaki

  Research Institute of Electrical Communication, Tohoku University

• Sato Shigeo

  Research Institute of Electrical Communication, Tohoku University

• Yuminaka Yasushi

  Graduate School of Science and Technology, Gunma University

• Horio Yoshihiko

  Research Institute of Electrical Communication, Tohoku University

• Madrenas Jordi

  Department of Electronics Engineering, Polytechnic University of Catalonia

Abstract

Neuromorphic engineering is a promising computing paradigm in next-generation information and communication technology. In particular, spiking neural networks are expected to reduce power consumption drastically owing to their event-driven operation. The spike-timing-dependent plasticity (STDP) rule, which learns from local spike-timing differences between spiking neurons, is a biologically plausible learning rule for spiking neural networks (SNNs). In this study, we designed and simulated an analog circuit that reproduces the multiplicative STDP rule, which is more flexible and adaptive to external signals. We also derived analytical expressions for the behavior of the proposed circuit. These results provide important insights for designing energy efficient neuromorphic devices for applications including edge computing.

Journal

• Nonlinear Theory and Its Applications, IEICE

  Nonlinear Theory and Its Applications, IEICE 12 (4), 685-694, 2021

  The Institute of Electronics, Information and Communication Engineers

Keywords

• spike-timing-dependent plasticity
• unsupervised learning
• analog circuit
• neuromorphic hardware
• edge computing

Details

• CRID: 1390852514696859136
• NII Article ID: 130008098002
• DOI: 10.1587/nolta.12.685
• ISSN: 21854106
• Web Site: https://www.jstage.jst.go.jp/article/nolta/12/4/12_685/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed