Training a multilayer dynamical spintronic network with standard machine learning tools to perform time series classification
This work addresses the energy efficiency challenge for time-series applications in AI hardware, though it is incremental as it adapts existing methods to a new physical system.
The authors tackled the problem of high energy cost in time-series processing by implementing a recurrent neural network in hardware using spintronic oscillators as dynamical neurons, achieving 89.83±2.91% accuracy on a sequential digits classification task, matching software performance.
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.