Spin splitting torque enabled artificial neuron with self-reset via synthetic antiferromagnetic coupling

TL;DR

This paper introduces a novel spintronic neuron that operates without external magnetic fields and includes a self-reset feature, demonstrating high accuracy in neural network tasks, thus advancing scalable and energy-efficient neuromorphic computing.

Contribution

The paper presents an altermagnet/SAF-based spintronic neuron that eliminates the need for external magnetic fields and incorporates a self-reset mechanism, improving scalability and practicality.

Findings

Achieved over 95% accuracy on MNIST datasets.

Demonstrated hardware feasibility for neuromorphic systems.

Eliminated external magnetic field requirement for neuron operation.

Abstract

Spintronic artificial neurons are intriguing building blocks for energy efficient Neuromorphic Computing (NC). Nevertheless, most contemporary implementations rely on symmetry breaking external in plane magnetic fields (H_X) for neuron operation, which limits scalability and hardware practicality. We experimentally demonstrate an altermagnet/Synthetic Antiferromagnetic Coupling (SAF) based spintronic neuron that uses out of plane spin ({\sigma}_Z) polarized spin-splitting torque to eliminate the necessity of an external H_X. The neuron device also features intrinsic self-reset function facilitated by built-in exchange coupling. Furthermore, the proposed device is validated for Spiking Neural Network (SNN) applications by achieving test accuracies of 95.99% and 94.36% on the MNIST and N-MNIST datasets, respectively. These results demonstrate the hardware feasibility and compatibility of the proposed spintronic neuron, highlighting its potential for compact, scalable and energy-efficient neuromorphic computing systems.