Discrete Anomalous Hall Resistance-based Quantized Convolutional Neural Network

Aijaz H. Lone*, Xuecui Zou, Hanrui Li, Nazek El-Atab, Hossein Fariborzi

*Corresponding author for this work

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

Abstract

Spintronic devices have shown promise for energy-efficient storage and neuromorphic computing. In this abstract, we present the realization of a spintronic device exhibiting discrete anomalous Hall resistance states. We attribute this discrete resistance behavior to the magnetic domain wall pinning and depinning and gradual switching of different magnetic layers. The number of resistance states is a function of the temperature. Furthermore, this discrete resistance behavior of the device allows us to employ these resistance states as weights in a quantized convolutional neural network. The network is trained and tested on the CIFAR-10 data set and the system achieves an accuracy of around 86.95%.

Original languageEnglish (US)
Title of host publication2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350338362
DOIs
StatePublished - 2023
Event2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023 - Sendai, Japan
Duration: May 15 2023May 19 2023

Publication series

Name2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023 - Proceedings

Conference

Conference2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023
Country/TerritoryJapan
CitySendai
Period05/15/2305/19/23

Keywords

  • Anomalous Hall effect
  • Discrete resistive states
  • Domain wall pinning
  • neuromorphic computing
  • Spintronics

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Electronic, Optical and Magnetic Materials
  • Instrumentation

Fingerprint

Dive into the research topics of 'Discrete Anomalous Hall Resistance-based Quantized Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this