Reservoir Computers with Random and Optimized Time-Shifts

TL;DR

This paper explores how applying random and optimized time-shifts to reservoir computer readouts can significantly improve accuracy and performance across various tasks, with a new optimization technique demonstrated through experiments.

Contribution

It introduces a simple method to optimize time-shifts in reservoir computing, enhancing accuracy and performance over traditional random shifts.

Findings

Random time-shifts improve accuracy and performance.

Optimized time-shifts outperform random shifts.

The proposed optimization method is effective in numerical tests.

Abstract

We investigate the effects of application of random time-shifts to the readouts of a reservoir computer in terms of both accuracy (training error) and performance (testing error.) For different choices of the reservoir parameters and different `tasks', we observe a substantial improvement in both accuracy and performance. We then develop a simple but effective technique to optimize the choice of the time-shifts, which we successfully test in numerical experiments.