Integrating magnetic skyrmions into neuromorphic computing could help improve hardware efficiency and computational power. However, developing a scalable implementation of the weighted sum of neuron signals - a core operation in neural networks - has remained a challenge. Here, we show that weighted sum operations can be performed in a compact, biologically-inspired manner by using the non-volatile and particle-like characteristics of magnetic skyrmions that make them easily countable and summable. The skyrmions are electrically generated in numbers proportional to an input with an efficiency given by a non-volatile weight. The chiral particles are then directed using localized current injections to a location where their presence is quantified through non-perturbative electrical measurements. Our experimental demonstration, which currently has two inputs, can be scaled to accommodate multiple inputs and outputs using a crossbar array design, potentially nearing the energy efficiency observed in biological systems.
@article{arxiv.2310.16909,
title = {Neuromorphic weighted sums with magnetic skyrmions},
author = {Tristan da Câmara Santa Clara Gomes and Yanis Sassi and Dédalo Sanz-Hernández and Sachin Krishnia and Sophie Collin and Marie-Blandine Martin and Pierre Seneor and Vincent Cros and Julie Grollier and Nicolas Reyren},
journal= {arXiv preprint arXiv:2310.16909},
year = {2025}
}