Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices

Abstract Ferrimagnetic materials with antiparallel exchange coupling, exhibit spin‐orbit‐torque‐induced dynamics, offering an emerging platform for realizing neuromorphic devices, such as artificial synapses. However, the state‐of‐the‐art artificial synapses based on ferrimagnet suffer from poor ana...

Full description

Saved in:
Bibliographic Details
Main Authors: Junwei Zeng, Binxuan Zhao, Yakun Liu, Teng Xu, Wanjun Jiang, Liang Fang, Jiahao Liu
Format: Article
Language:English
Published: Wiley-VCH 2025-04-01
Series:Advanced Electronic Materials
Subjects:
Online Access:https://doi.org/10.1002/aelm.202400591
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199256206409728
author Junwei Zeng
Binxuan Zhao
Yakun Liu
Teng Xu
Wanjun Jiang
Liang Fang
Jiahao Liu
author_facet Junwei Zeng
Binxuan Zhao
Yakun Liu
Teng Xu
Wanjun Jiang
Liang Fang
Jiahao Liu
author_sort Junwei Zeng
collection DOAJ
description Abstract Ferrimagnetic materials with antiparallel exchange coupling, exhibit spin‐orbit‐torque‐induced dynamics, offering an emerging platform for realizing neuromorphic devices, such as artificial synapses. However, the state‐of‐the‐art artificial synapses based on ferrimagnet suffer from poor analog switching linearity, which serves as a bottleneck for achieving complex tasks with high accuracy in neuromorphic computing. Here, an artificial synapse is reported with high‐weight update linearity in a compensated ferrimagnetic crossbar device. In particular, the linear weight update of the synapses is enhanced by engineering the current density distribution. Using experimentally derived device parameters, handwritten digit recognition can be achieved with an accuracy of over 95% in a three‐layer fully connected artificial neural network. The work provides a universal method to improve the synaptic linearity, which also paves the way for applying the spin‐orbit device in neuromorphic computing.
format Article
id doaj-art-3ff9e162a7e84232aa97ccf6f475ed62
institution OA Journals
issn 2199-160X
language English
publishDate 2025-04-01
publisher Wiley-VCH
record_format Article
series Advanced Electronic Materials
spelling doaj-art-3ff9e162a7e84232aa97ccf6f475ed622025-08-20T02:12:40ZengWiley-VCHAdvanced Electronic Materials2199-160X2025-04-01115n/an/a10.1002/aelm.202400591Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic DevicesJunwei Zeng0Binxuan Zhao1Yakun Liu2Teng Xu3Wanjun Jiang4Liang Fang5Jiahao Liu6College of Advanced Interdisciplinary Studies & Hunan Provincial Key Laboratory of Novel Nano‐Optoelectronic Information Materials and Devices National University of Defense Technology Changsha Hunan 410073 ChinaAnhui Province Key Laboratory of Low‐Energy Quantum Materials and Devices High Magnetic Field Laboratory HFIPS Chinese Academy of Sciences Hefei 230031 ChinaArtificial Intelligence Research Center Defense Innovation Institute Beijing 100072 ChinaAnhui Province Key Laboratory of Low‐Energy Quantum Materials and Devices High Magnetic Field Laboratory HFIPS Chinese Academy of Sciences Hefei 230031 ChinaState Key Laboratory of Low‐Dimensional Quantum Physics and Department of Physics Tsinghua University Beijing 100084 ChinaInstitute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha 410073 ChinaCollege of Advanced Interdisciplinary Studies & Hunan Provincial Key Laboratory of Novel Nano‐Optoelectronic Information Materials and Devices National University of Defense Technology Changsha Hunan 410073 ChinaAbstract Ferrimagnetic materials with antiparallel exchange coupling, exhibit spin‐orbit‐torque‐induced dynamics, offering an emerging platform for realizing neuromorphic devices, such as artificial synapses. However, the state‐of‐the‐art artificial synapses based on ferrimagnet suffer from poor analog switching linearity, which serves as a bottleneck for achieving complex tasks with high accuracy in neuromorphic computing. Here, an artificial synapse is reported with high‐weight update linearity in a compensated ferrimagnetic crossbar device. In particular, the linear weight update of the synapses is enhanced by engineering the current density distribution. Using experimentally derived device parameters, handwritten digit recognition can be achieved with an accuracy of over 95% in a three‐layer fully connected artificial neural network. The work provides a universal method to improve the synaptic linearity, which also paves the way for applying the spin‐orbit device in neuromorphic computing.https://doi.org/10.1002/aelm.202400591artificial synapsesferrimagnetneuromorphic computingspin‐orbit torquespintronics
spellingShingle Junwei Zeng
Binxuan Zhao
Yakun Liu
Teng Xu
Wanjun Jiang
Liang Fang
Jiahao Liu
Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
Advanced Electronic Materials
artificial synapses
ferrimagnet
neuromorphic computing
spin‐orbit torque
spintronics
title Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
title_full Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
title_fullStr Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
title_full_unstemmed Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
title_short Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices
title_sort linear weight update synaptic responses in ferrimagnetic neuromorphic devices
topic artificial synapses
ferrimagnet
neuromorphic computing
spin‐orbit torque
spintronics
url https://doi.org/10.1002/aelm.202400591
work_keys_str_mv AT junweizeng linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT binxuanzhao linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT yakunliu linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT tengxu linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT wanjunjiang linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT liangfang linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices
AT jiahaoliu linearweightupdatesynapticresponsesinferrimagneticneuromorphicdevices