Reservoir Computing Generalized

TL;DR

This paper introduces generalized reservoir computing (GRC), a framework that enables the use of unconventional physical substances with non-reproducible dynamics for information processing, expanding the potential materials for physical neural networks.

Contribution

The authors propose GRC, allowing reservoir computing with substances that have non-reproducible responses, and demonstrate its ability to utilize spatiotemporal chaos for complex computations.

Findings

GRC can reliably process inputs from non-reproducible substances.

Unconventional materials like spin-torque oscillators are viable for reservoir computing.

Spatiotemporal chaos can be harnessed for complex nonlinear dynamics in computation.

Abstract

A physical neural network (PNN) has both the strong potential to solve machine learning tasks and intrinsic physical properties, such as high-speed computation and energy efficiency. Reservoir computing (RC) is an excellent framework for implementing an information processing system with a dynamical system by attaching a trained readout, thus accelerating the wide use of unconventional materials for a PNN. However, RC requires the dynamics to reproducibly respond to input sequence, which limits the type of substance available for building information processors. Here we propose a novel framework called generalized reservoir computing (GRC) by turning this requirement on its head, making conventional RC a special case. Using substances that do not respond the same to identical inputs (e.g., a real spin-torque oscillator), we propose mechanisms aimed at obtaining a reliable output and show that processed inputs in the unconventional substance are retrievable. Finally, we demonstrate that, based on our framework, spatiotemporal chaos, which is thought to be unusable as a computational resource, can be used to emulate complex nonlinear dynamics, including large scale spatiotemporal chaos. Overall, our framework removes the limitation to building an information processing device and opens a path to constructing a computational system using a wider variety of physical dynamics.