Composite FORCE learning of chaotic echo state networks for time-series prediction
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.
Keywords
Cite
@article{arxiv.2207.02420,
title = {Composite FORCE learning of chaotic echo state networks for time-series prediction},
author = {Yansong Li and Kai Hu and Kohei Nakajima and Yongping Pan},
journal= {arXiv preprint arXiv:2207.02420},
year = {2024}
}
Comments
Submitted to 2022 Chinese Control Conference