Training a multilayer dynamical spintronic network with standard machine learning tools to perform time series classification

TL;DR

This paper demonstrates that a multilayer spintronic oscillator network can be trained with standard machine learning tools to perform time series classification efficiently, matching software neural network performance.

Contribution

It introduces a hardware implementation of recurrent neural networks using spintronic oscillators and shows how to train them with backpropagation through time.

Findings

Achieved 89.83% accuracy on digit classification.

Provided guidelines for tuning oscillator parameters.

Validated hardware neural network performance against software models.

Abstract

The ability to process time-series at low energy cost is critical for many applications. Recurrent neural network, which can perform such tasks, are computationally expensive when implementing in software on conventional computers. Here we propose to implement a recurrent neural network in hardware using spintronic oscillators as dynamical neurons. Using numerical simulations, we build a multi-layer network and demonstrate that we can use backpropagation through time (BPTT) and standard machine learning tools to train this network. Leveraging the transient dynamics of the spintronic oscillators, we solve the sequential digits classification task with $89.83\pm2.91~\%$ accuracy, as good as the equivalent software network. We devise guidelines on how to choose the time constant of the oscillators as well as hyper-parameters of the network to adapt to different input time scales.