Neuromorphic Computing through Time-Multiplexing with a Spin-Torque Nano-Oscillator

TL;DR

This paper demonstrates that spin-torque nano-oscillators can serve as compact, reliable neurons for neuromorphic computing, enabling efficient reservoir computing with high performance in a miniaturized chip design.

Contribution

It introduces the use of spin-torque nano-oscillators as neurons in neuromorphic chips and details their application in reservoir computing.

Findings

Nano-oscillators can reliably implement neurons at submicrometer scale.

They can perform reservoir computing with high accuracy.

The approach supports miniaturization of neuromorphic hardware.

Abstract

Fabricating powerful neuromorphic chips the size of a thumb requires miniaturizing their basic units: synapses and neurons. The challenge for neurons is to scale them down to submicrometer diameters while maintaining the properties that allow for reliable information processing: high signal to noise ratio, endurance, stability, reproducibility. In this work, we show that compact spin-torque nano-oscillators can naturally implement such neurons, and quantify their ability to realize an actual cognitive task. In particular, we show that they can naturally implement reservoir computing with high performance and detail the recipes for this capability.