Optimization of parameters of echo state network and its application to underwater robot

Echo state networks (ESNs) use a recurrent artificial neural network as a reservoir. Finding a good one depends on choosing the right parameters for the generation of the reservoir, intuition and luck. The method proposed in this article eliminates the need for the tuning by hand by replacing it with a double evolutionary computation. First a broad search to find the right parameters, which generate the reservoir, is used. Then a search directly on the connectivity matrices fine-tunes the ESN. Both steps show improvements over other known methods for an experimental limit-cycle dataset of the Twin-Burger underwater robot.