Reservoir Computing Using Complex Systems

TL;DR

This paper explores the use of a memristive chaotic oscillator as a physical reservoir in reservoir computing, demonstrating its effectiveness in non-temporal tasks and analyzing how system dynamics influence performance.

Contribution

It introduces a novel reservoir computing system based on a memristive chaotic oscillator and investigates hyperparameter optimization for improved computational capability.

Findings

Reservoir performance varies with hyperparameter tuning.

Physical system dynamics directly affect prediction accuracy.

The system successfully approximates polynomials and Lorenz trajectories.

Abstract

Reservoir Computing is an emerging machine learning framework which is a versatile option for utilising physical systems for computation. In this paper, we demonstrate how a single node reservoir, made of a simple electronic circuit, can be employed for computation and explore the available options to improve the computational capability of the physical reservoirs. We build a reservoir computing system using a memristive chaotic oscillator as the reservoir. We choose two of the available hyperparameters to find the optimal working regime for the reservoir, resulting in two reservoir versions. We compare the performance of both the reservoirs in a set of three non-temporal tasks: approximating two non-chaotic polynomials and a chaotic trajectory of the Lorenz time series. We also demonstrate how the dynamics of the physical system plays a direct role in the reservoir's hyperparameters and hence in the reservoir's prediction ability.