Artificial neurons based on antiferromagnetic auto-oscillators as a platform for neuromorphic computing

Abstract

Spiking artificial neurons emulate the voltage spikes of biological neurons, and constitute the building blocks of a new class of energy efficient, neuromorphic computing systems. Antiferromagnetic materials can, in theory, be used to construct spiking artificial neurons. When configured as a neuron, the magnetizations in antiferromagnetic materials have an effective inertia that gives them intrinsic characteristics that closely resemble biological neurons, in contrast with conventional artificial spiking neurons. It is shown here that antiferromagnetic neurons have a spike duration on the order of a picosecond, a power consumption of about 10^-3 pJ per synaptic operation, and built-in features that directly resemble biological neurons, including response latency, refraction, and inhibition. It is also demonstrated that antiferromagnetic neurons interconnected into physical neural networks can perform unidirectional data processing even for passive symmetrical interconnects. Flexibility of antiferromagnetic neurons is illustrated by simulations of simple neuromorphic circuits realizing Boolean logic gates and controllable memory loops.

arXiv comment18 pages, 17 figures

References in corpus (17)

• Electrical switching of an antiferromagnet
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• Antidamping torque-induced switching in biaxial antiferromagnetic insulators
• Subterahertz spin pumping from an insulating antiferromagnet
• Josephson junction simulation of neurons
• Transformation of spin current by antiferromagnetic insulators
• The Cost of Training NLP Models: A Concise Overview
• Room temperature antiferromagnetic resonance and inverse spin-Hall voltage in canted antiferromagnets
• CMOS compatible W/CoFeB/MgO spin Hall nano-oscillators with wide frequency tunability
• Micromagnetic modeling of Terahertz oscillations in an antiferromagnetic material driven by spin-Hall effect
• On-chip learning for domain wall synapse based Fully Connected Neural Network
• Narrow-band tunable THz detector in antiferromagnets via Néel spin-orbit torque and spin-transfer torque
• Bilayer-skyrmion-based design of neuron and synapse for spiking neural network
• Hardware realization of the multiply and accumulate operation on radio-frequency signals with magnetic tunnel junctions
• Bias-free spin-wave phase shifter for magnonic logic
• Precessional spin-torque dynamics in biaxial antiferromagnets
• Antiferromagnet-Based Neuromorphics Using Dynamics of Topological Charges