Skip to main navigation Skip to search Skip to main content

Realization of neural coding by stochastic switching of magnetic tunnel junction

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we present the realization of neural rate coding with probabilistic spike trains by using two back-to-back magnetic tunnel junctions (MTJs) for the bio-inspired computing applications. By exploiting the intrinsic stochastic switching of the MTJ device between two different resistance states, an analog stimulus can be converted into a probabilistic spike train and its spike rate can be modulated by the switching probability, which depends on the magnitude of the stimulus. To implement such conversion, we propose a hybrid CMOS/MTJ circuit. By using a physics-based MTJ compact model and a commercial CMOS 40nm design kit, its functionality has been validated. Additionally, we also investigate the relationship between switching probability and stimulus by Monte Carlo simulations.

Original languageEnglish
Title of host publication2015 15th Non-Volatile Memory Technology Symposium, NVMTS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509021260
DOIs
StatePublished - 20 Apr 2016
Event15th Non-Volatile Memory Technology Symposium, NVMTS 2015 - Beijing, China
Duration: 12 Oct 201514 Oct 2015

Publication series

Name2015 15th Non-Volatile Memory Technology Symposium, NVMTS 2015

Conference

Conference15th Non-Volatile Memory Technology Symposium, NVMTS 2015
Country/TerritoryChina
CityBeijing
Period12/10/1514/10/15

Keywords

  • Monte Carlo simulations
  • bio-inspired computing
  • magnetic tunnel junction (MTJ)
  • neural rate coding
  • probabilistic spike train
  • stochatic switching

Fingerprint

Dive into the research topics of 'Realization of neural coding by stochastic switching of magnetic tunnel junction'. Together they form a unique fingerprint.

Cite this