Composite FORCE learning of chaotic echo state networks for time-series prediction

TL;DR

This paper introduces a composite FORCE learning method using recursive least squares to improve the training and prediction accuracy of chaotic echo state networks in time-series forecasting.

Contribution

It presents a novel composite FORCE learning approach that enhances parameter convergence for chaotic ESNs by leveraging dynamic regressor extension and memory data exploitation.

Findings

Significantly improved learning performance on chaotic time series

Enhanced prediction accuracy over existing methods

Effective training of ESNs with spontaneous chaotic activity

Abstract

Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output only by training output connection weights. First-order reduced and controlled error (FORCE) learning is an online supervised training approach that can change the chaotic activity of ESNs into specified activity patterns. This paper proposes a composite FORCE learning method based on recursive least squares to train ESNs whose initial activity is spontaneously chaotic, where a composite learning technique featured by dynamic regressor extension and memory data exploitation is applied to enhance parameter convergence. The proposed method is applied to a benchmark problem about predicting chaotic time series generated by the Mackey-Glass system, and numerical results have shown that it significantly improves learning and prediction performances compared with existing methods.