An approach to reservoir computing design and training

Reservoir computing is a framework for computation like a recurrent neural network that allows for the black box modeling of dynamical systems. In contrast to other recurrent neural network approaches, reservoir computing does not train the input and internal weights of the network, only the readout is trained. However it is necessary to adjust parameters to create a “good” reservoir for a given application. In this study we introduce a method, called RCDESIGN (reservoir computing and design training). RCDESIGN combines an evolutionary algorithm with reservoir computing and simultaneously looks for the best values of parameters, topology and weight matrices without rescaling the reservoir matrix by the spectral radius. The idea of adjust the spectral radius within the unit circle in the complex plane comes from the linear system theory. However, this argument does not necessarily apply to nonlinear systems, which is the case of reservoir computing. The results obtained with the proposed method are compared with results obtained by a genetic algorithm search for global parameters generation of reservoir computing. Four time series were used to validate RCDESIGN.

► We introduce a method, called RCDESIGN (reservoir computing and design training).
► RCDESIGN optimizes reservoir parameters, topology and reservoir weights simultaneously, without the spectral radius rescaling.
► RCDESIGN performs well, since the real dynamics of the reservoir can only be found with the system in use.
► We verified that the proposed method is good for forecasting four distinct time series.