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

TL;DR

This paper demonstrates the hardware implementation of multiply and accumulate operations on RF signals using magnetic tunnel junctions, enabling low-power, high-speed neural network processing directly at the antenna.

Contribution

It provides the first experimental validation of magnetic tunnel junctions performing RF signal multiplication and MAC operations for neural network applications.

Findings

Magnetic tunnel junctions can perform RF power multiplication with tunable weights.

Two magnetic tunnel junctions in series can implement MAC operations.

The system successfully classifies RF signals using the proposed hardware.

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.