Hardware realization of the multiply and accumulate operation on radio-frequency signals with magnetic tunnel junctions

Abstract

Artificial neural networks are a valuable tool for radio-frequency (RF) signal classification in many applications, but digitization of analog signals and the use of general purpose hardware non-optimized for training make the process slow and energetically costly. Recent theoretical work has proposed to use nano-devices called magnetic tunnel junctions, which exhibit intrinsic RF dynamics, to implement in hardware the Multiply and Accumulate (MAC) operation, a key building block of neural networks, directly using analogue RF signals. In this article, we experimentally demonstrate that a magnetic tunnel junction can perform multiplication of RF powers, with tunable positive and negative synaptic weights. Using two magnetic tunnel junctions connected in series we demonstrate the MAC operation and use it for classification of RF signals. These results open the path to embedded systems capable of analyzing RF signals with neural networks directly after the antenna, at low power cost and high speed.

arXiv comment10 pages, 4 figures

References in corpus (9)

• Over the Air Deep Learning Based Radio Signal Classification
• 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks
• Vowel recognition with four coupled spin-torque nano-oscillators
• Large microwave generation from d.c. driven magnetic vortex oscillators in magnetic tunnel junctions
• Large-Scale Optical Neural Networks based on Photoelectric Multiplication
• Giant spin-torque diode sensitivity at low input power in the absence of bias magnetic field
• Experimental demonstration of a rapid sweep-tuned spectrum analyzer with temporal resolution based on a spin-torque nano-oscillator
• Wireless communication between two magnetic tunnel junctions acting as oscillator and diode
• Spintronic nano-scale harvester of broadband microwave energy

Cited by in corpus (4)

• Quantum materials for energy-efficient neuromorphic computing
• Reconfigurable Reservoir Computing in a Magnetic Metamaterial
• Exploring Multifunctionality in MgO-Based Magnetic Tunnel Junctions with Coexisting Magnetoresistance and Memristive Properties
• Artificial neurons based on antiferromagnetic auto-oscillators as a platform for neuromorphic computing