Stochastic spin-orbit-torque device as the STDP synapse for spiking neural networks  

作　　者：Haotian Li Liyuan Li Kaiyuan Zhou Chunjie Yan Zhenyu Gao Zishuang Li Ronghua Liu 

机构地区：[1]National Laboratory of Solid State Microstructures,Jiangsu Provincial Key Laboratory for Nanotechnology,School of Physics,Nanjing University,Nanjing 210093,China

出　　处：《Science China(Physics,Mechanics & Astronomy)》2023年第5期188-194,共7页中国科学：物理学、力学、天文学（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.12074178);the Open Research Fund of Jiangsu Provincial Key Laboratory for Nanotechnology.

摘　　要：Neuromorphic hardware,as a non-Von Neumann architecture,has better energy efficiency and parallelism than the conventional computer.Here,with the numerical modeling spin-orbit torque(SOT)device using current-induced SOT and Joule heating effects,we acquire its magnetization stochastic switching probability as a function of the interval time of input current pulses and use it to mimic the spike-timing-dependent plasticity learning behavior like actual brain working.We further demonstrate that the artificial spiking neural network(SNN)built by this SOT device can perform unsupervised handwritten digit recognition with an accuracy of 80%and logic operation learning.Our work provides a new clue to achieving SNN-based neuromorphic hardware using high-energy efficiency and nonvolatile spintronics nanodevices.

关 键 词：spin-orbit torque neuromorphic hardware spiking neural network stochastic magnetization reversal 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] O469[自动化与计算机技术—控制科学与工程]