A novel echo state network design method based on differential evolution algorithm

Echo state network (ESN) is a powerful tool for nonlinear system modeling. However, the random setting of structure (mainly the reservoir) may degrade its estimation accuracy. To create the optimal reservoir for a given task, a novel ESN design method based on differential evolution algorithm is proposed. Firstly, the weight matrix of reservoir is constructed via the singular value decomposition (SVD). Then, the corresponding singular values are optimized by using a variant of differential evolution algorithm. Finally, some comparisons are made which show that the proposed ESN has better training performance than other deterministic and evolutionary algorithm based ESNs.