A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Data

TL;DR

This paper introduces MARC, a meta-learning method for reservoir computing that reduces data requirements for time series prediction of dynamical systems, especially when data is scarce.

Contribution

The paper proposes a novel meta-learning framework for reservoir computing that automatically learns model structures from related processes, improving prediction with limited data.

Findings

Outperforms existing meta-learning techniques on benchmark problems

Successfully predicts chaotic systems with less data

Demonstrates robustness across different dynamical systems

Abstract

Recent research has established the effectiveness of machine learning for data-driven prediction of the future evolution of unknown dynamical systems, including chaotic systems. However, these approaches require large amounts of measured time series data from the process to be predicted. When only limited data is available, forecasters are forced to impose significant model structure that may or may not accurately represent the process of interest. In this work, we present a Meta-learning Approach to Reservoir Computing (MARC), a data-driven approach to automatically extract an appropriate model structure from experimentally observed "related" processes that can be used to vastly reduce the amount of data required to successfully train a predictive model. We demonstrate our approach on a simple benchmark problem, where it beats the state of the art meta-learning techniques, as well as a challenging chaotic problem.