Spin-Orbit Torque Induced Spike-Timing Dependent Plasticity

TL;DR

This paper introduces a novel ferromagnet-heavy metal heterostructure device that uses spin-orbit torque to emulate spike-timing dependent plasticity, enabling energy-efficient and reliable synaptic behavior for neuromorphic computing.

Contribution

It proposes a new device architecture utilizing spin-orbit torque for synaptic plasticity, with potential for high-density neural networks and ultra-low energy consumption.

Findings

Achieves pico-Joule level energy per synaptic event

Decouples spike transmission and programming current paths

Suitable for ultra-dense neural network architectures

Abstract

Nanoelectronic devices that mimic the functionality of synapses are a crucial requirement for performing cortical simulations of the brain. In this work we propose a ferromagnet-heavy metal heterostructure that employs spin-orbit torque to implement Spike-Timing Dependent Plasticity. The proposed device offers the advantage of decoupled spike transmission and programming current paths, thereby leading to reliable operation during online learning. Possible arrangement of such devices in a crosspoint architecture can pave the way for ultra-dense neural networks. Simulation studies indicate that the device has the potential of achieving pico-Joule level energy consumption (maximum 2 pJ per synaptic event) which is comparable to the energy consumption for synaptic events in biological synapses.