Vowel recognition with four coupled spin-torque nano-oscillators

TL;DR

This paper demonstrates that a hardware network of four spin-torque nano-oscillators can recognize spoken vowels by leveraging their high tunability and mutual coupling, showcasing potential for neuromorphic computing.

Contribution

The study introduces a method to train a small spintronic neural network for vowel recognition using real-time tuning, highlighting the role of non-linear dynamics in pattern classification.

Findings

High recognition accuracy achieved with four oscillators

Effective real-time tuning enables pattern learning

Non-linear dynamics facilitate complex classification

Abstract

Substantial evidence indicates that the brain uses principles of non-linear dynamics in neural processes, providing inspiration for computing with nanoelectronic devices. However, training neural networks composed of dynamical nanodevices requires finely controlling and tuning their coupled oscillations. In this work, we show that the outstanding tunability of spintronic nano-oscillators can solve this challenge. We successfully train a hardware network of four spin-torque nano-oscillators to recognize spoken vowels by tuning their frequencies according to an automatic real-time learning rule. We show that the high experimental recognition rates stem from the high frequency tunability of the oscillators and their mutual coupling. Our results demonstrate that non-trivial pattern classification tasks can be achieved with small hardware neural networks by endowing them with non-linear dynamical features: here, oscillations and synchronization. This demonstration is a milestone for spintronics-based neuromorphic computing.