Small-World Echo State Networks for Nonlinear Time-Series Prediction

Echo state network (ESN) is a reservoir computing approach for efficiently training recurrent neural networks. However, it sometimes suffers from poor performance and robustness due to the non-trainable reservoir. This paper proposes a novel computational framework for ESNs to improve prediction performance and robustness. A small-world network is applied as the reservoir topology, a biologically plausible unsupervised learning method named dual-threshold Bienenstock-Cooper-Munro learning rule is applied to adjust reservoir weights adaptively, and a recursive least-squares-based composite learning algorithm is introduced to update readout weights. The proposed method is compared with several kinds of ESNs on the Mackey-Glass system, a benchmark problem of nonlinear time-series prediction. Simulation results have shown that the proposed method not only achieves the best prediction performance but also exhibits remarkable robustness against noise.