Multilayer spintronic neural networks with radio-frequency connections

TL;DR

This paper demonstrates a scalable multilayer spintronic neural network using magnetic tunnel junctions that processes RF signals with high accuracy and ultra-low power, advancing AI hardware technology.

Contribution

It introduces a novel method to connect spintronic nano-components into multilayer neural networks that operate via RF signals, enabling scalable and efficient AI hardware.

Findings

Achieved 97.7% accuracy in RF input classification with a 9-junction network.

Demonstrated large-scale nanoscale networks can identify RF signals with minimal power consumption.

Showed potential for spintronic neural networks to outperform current AI hardware in power efficiency.

Abstract

Spintronic nano-synapses and nano-neurons perform complex cognitive computations with high accuracy thanks to their rich, reproducible and controllable magnetization dynamics. These dynamical nanodevices could transform artificial intelligence hardware, provided that they implement state-of-the art deep neural networks. However, there is today no scalable way to connect them in multilayers. Here we show that the flagship nano-components of spintronics, magnetic tunnel junctions, can be connected into multilayer neural networks where they implement both synapses and neurons thanks to their magnetization dynamics, and communicate by processing, transmitting and receiving radio frequency (RF) signals. We build a hardware spintronic neural network composed of nine magnetic tunnel junctions connected in two layers, and show that it natively classifies nonlinearly-separable RF inputs with an accuracy of 97.7%. Using physical simulations, we demonstrate that a large network of nanoscale junctions can achieve state-of the-art identification of drones from their RF transmissions, without digitization, and consuming only a few milliwatts, which is a gain of more than four orders of magnitude in power consumption compared to currently used techniques. This study lays the foundation for deep, dynamical, spintronic neural networks.