Microwave neural processing and broadcasting with spintronic nano-oscillators

TL;DR

This paper demonstrates that spintronic nano-oscillators can serve as dense, tunable artificial neurons capable of learning complex tasks like vowel classification, advancing nanoscale neuromorphic hardware.

Contribution

It introduces spintronic nano-oscillators as a new hardware platform for artificial neurons and experimentally shows their ability to perform complex classification tasks.

Findings

Ensemble of four coupled oscillators learned to classify twelve American vowels.

Spintronic nano-oscillators can be densely interconnected via electromagnetic signals.

The approach achieves complex task performance with nanoscale neural hardware.

Abstract

Can we build small neuromorphic chips capable of training deep networks with billions of parameters? This challenge requires hardware neurons and synapses with nanometric dimensions, which can be individually tuned, and densely connected. While nanosynaptic devices have been pursued actively in recent years, much less has been done on nanoscale artificial neurons. In this paper, we show that spintronic nano-oscillators are promising to implement analog hardware neurons that can be densely interconnected through electromagnetic signals. We show how spintronic oscillators maps the requirements of artificial neurons. We then show experimentally how an ensemble of four coupled oscillators can learn to classify all twelve American vowels, realizing the most complicated tasks performed by nanoscale neurons.