用于人工神经元的双氧化镁基垂直磁隧道结

Double MgO-Based Perpendicular Magnetic Tunnel Junction for Artificial Neuron.

作者信息

Kim Dong Won, Yi Woo Seok, Choi Jin Young, Ashiba Kei, Baek Jong Ung, Jun Han Sol, Kim Jae Joon, Park Jea Gun

机构信息

Department of Nanoscale Semiconductor Engineering, Hanyang University, Seoul, South Korea.

Department of Creative IT Engineering, Pohang University of Science and Technology, Pohang, South Korea.

出版信息

Front Neurosci. 2020 Apr 30;14:309. doi: 10.3389/fnins.2020.00309. eCollection 2020.

DOI:10.3389/fnins.2020.00309

PMID:32425744

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7204637/

Abstract

A perpendicular spin transfer torque (p-STT)-based neuron was developed for a spiking neural network (SNN). It demonstrated the integration behavior of a typical neuron in an SNN; in particular, the integration behavior corresponding to magnetic resistance change gradually increased with the input spike number. This behavior occurred when the spin electron directions between double CoFeB free and pinned layers in the p-STT-based neuron were switched from parallel to antiparallel states. In addition, a neuron circuit for integrate-and-fire operation was proposed. Finally, pattern-recognition simulation was performed for a single-layer SNN.

摘要

一种基于垂直自旋转移矩（p-STT）的神经元被开发用于脉冲神经网络（SNN）。它展示了SNN中典型神经元的积分行为；特别是，与磁阻变化相对应的积分行为随着输入脉冲数逐渐增加。当基于p-STT的神经元中双CoFeB自由层和固定层之间的自旋电子方向从平行状态切换到反平行状态时，就会出现这种行为。此外，还提出了一种用于积分发放操作的神经元电路。最后，对单层SNN进行了模式识别模拟。