Insight into delay based reservoir computing via eigenvalue analysis

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 analysing the small signal response of the reservoir. Our results suggest that any dynamical system used as a reservoir can be analysed 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.

Automated summary

This paper provides a deep insight into the computation capability of delay based reservoir computing through an eigenvalue analysis and finds a connection between task-independent memory capacity and the eigenvalue spectrum of the dynamical system. The performance of reservoir computing can be predicted by analyzing the small signal response of the reservoir. Analysis can be applied to any dynamical system used as a reservoir.