Post-processing methods for delay embedding and feature scaling of reservoir computers

Tools

Jaurigue, Jonnel and Robertson, Joshua and Hurtado, Antonio and Jaurigue, Lina and Lüdge, Kathy (2025) Post-processing methods for delay embedding and feature scaling of reservoir computers. Communications Engineering, 4 (1). 10. ISSN 2731-3395 (https://doi.org/10.1038/s44172-024-00330-0)

[thumbnail of Jaurigue-etal-2025-Post-processing-methods-for-delay-embedding-and-feature-scaling-of-reservoir-computers]
Preview
 Text. Filename: Jaurigue-etal-2025-Post-processing-methods-for-delay-embedding-and-feature-scaling-of-reservoir-computers.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (2MB)| Preview

Abstract

Reservoir computing is a machine learning method that is well-suited for complex time series prediction tasks. Both delay embedding and the projection of input data into a higher-dimensional space play important roles in enabling accurate predictions. We establish simple post-processing methods that train on past node states at uniformly or randomly-delayed timeshifts. These methods improve reservoir computer prediction performance through increased feature dimension and/or better delay embedding. Here we introduce the multi-random-timeshifting method that randomly recalls previous states of reservoir nodes. The use of multi-random-timeshifting allows for smaller reservoirs while maintaining large feature dimensions, is computationally cheap to optimise, and is our preferred post-processing method. For experimentalists, all our post-processing methods can be translated to readout data sampled from physical reservoirs, which we demonstrate using readout data from an experimentally-realised laser reservoir system.

ORCID iDs

Jaurigue, Jonnel, Robertson, Joshua ORCID logoORCID: https://orcid.org/0000-0001-6316-5265, Hurtado, Antonio ORCID logoORCID: https://orcid.org/0000-0002-4448-9034, Jaurigue, Lina and Lüdge, Kathy;
CORE (COnnecting REpositories)