Insight into Delay Based Reservoir Computing via Eigenvalue Analysis

TL;DR

This paper provides a theoretical framework linking the eigenvalue spectrum of delay-based reservoir systems to their computational memory capacity, demonstrated through a photonic laser example.

Contribution

It introduces an eigenvalue analysis method to predict reservoir computing performance, applicable to various dynamical systems.

Findings

Eigenvalues with real parts near zero optimize performance

Memory capacity correlates with eigenvalue spectrum

Photonic laser reservoir confirms theoretical predictions

Abstract

In this paper we give a profound insight into the computation capability of delay-based reservoir computing via an eigenvalue analysis. We concentrate on the task-independent memory capacity to quantify the reservoir performance and compare these with the eigenvalue spectrum of the dynamical system. We show that these two quantities are deeply connected, and thus the reservoir computing performance is predictable by analyzing the small signal response of the reservoir. Our results suggest that any dynamical system used as a reservoir can be analyzed in this way. We apply our method exemplarily to a photonic laser system with feedback and compare the numerically computed recall capabilities with the eigenvalue spectrum. Optimal performance is found for a system with the eigenvalues having real parts close to zero and off-resonant imaginary parts.