Analogue spin-orbit torque device for artificial-neural-network-based associative memory operation

被引：155

作者：

Borders, William A. ^{[1
]}

Akima, Hisanao ^{[1
]}

Fukami, Shunsuke ^{[1
,2
,3
,4
]}

Moriya, Satoshi ^{[1
]}

Kurihara, Shouta ^{[1
]}

Horio, Yoshihiko ^{[1
]}

Sato, Shigeo ^{[1
]}

Ohno, Hideo ^{[1
,2
,3
,4
,5
]}

机构：

[1] Tohoku Univ, Res Inst Elect Commun, Lab Nanoelect & Spintron, Sendai, Miyagi 9808577, Japan

[2] Tohoku Univ, Ctr Spintron Integrated Syst, Sendai, Miyagi 9808577, Japan

[3] Tohoku Univ, Ctr Innovat Integrated Elect Syst, Sendai, Miyagi 9800845, Japan

[4] Tohoku Univ, Ctr Spintron Res Network, Sendai, Miyagi 9808577, Japan

[5] Tohoku Univ, WPI Adv Inst Mat Res, Sendai, Miyagi 9808577, Japan

来源：

APPLIED PHYSICS EXPRESS | 2017年 / 10卷 / 01期

关键词：

SYNAPSE; SYSTEM;

D O I：

10.7567/APEX.10.013007

中图分类号：

O59 [应用物理学];

学科分类号：

摘要：

We demonstrate associative memory operations reminiscent of the brain using nonvolatile spintronics devices. Antiferromagnet-ferromagnet bilayer-based Hall devices, which show analogue-like spin-orbit torque switching under zero magnetic fields and behave as artificial synapses, are used. An artificial neural network is used to associate memorized patterns from their noisy versions. We develop a network consisting of a field-programmable gate array and 36 spin-orbit torque devices. An effect of learning on associative memory operations is successfully confirmed for several 3 x 3-block patterns. A discussion on the present approach for realizing spintronics-based artificial intelligence is given. (c) 2017 The Japan Society of Applied Physics

引用

页数：4

共 17 条

[1]

ACKLEY DH, 1985, COGNITIVE SCI, V9, P147

[2] STATISTICAL NEURODYNAMICS OF ASSOCIATIVE MEMORY [J].