Convolutions with Radio-Frequency Spin-Diodes

TL;DR

This paper demonstrates that simple metallic spin-diodes can perform RF signal classification and convolutional filtering, achieving high accuracy on image datasets, offering a scalable hardware solution for RF processing.

Contribution

It introduces the use of metallic spin-diodes for RF classification and convolution, simplifying spintronic devices for scalable hardware implementation.

Findings

Chains of four spin-diodes can perform 2x2 pixel filters.

Achieved 88% top-1 accuracy on Fashion-MNIST with hardware-in-the-loop.

Hardware filters closely match software performance with minimal noise effects.

Abstract

The classification of radio-frequency (RF) signals is crucial for applications in robotics, traffic control, and medical devices. Spintronic devices, which respond to RF signals via ferromagnetic resonance, offer a promising solution. Recent studies have shown that a neural network of nanoscale magnetic tunnel junctions can classify RF signals without digitization. However, the complexity of these junctions poses challenges for rapid scaling. In this work, we demonstrate that simple spintronic devices, known as metallic spin-diodes, can effectively perform RF classification. These devices consist of NiFe/Pt bilayers and can implement weighted sums of RF inputs. We experimentally show that chains of four spin-diodes can execute 2x2 pixel filters, achieving high-quality convolutions on the Fashion-MNIST dataset. Integrating the hardware spin-diodes in a software network, we achieve a top-1 accuracy of 88 \% on the first 100 images, compared to 88.4 \% for full software with noise, and 90 \% without noise.