Reservoir and reservoir computing system

[0020]Hereinafter, some embodiments of the present invention will be described. The embodiments do not limit the invention according to the claims, and all the combinations of the features described in the embodiments are not necessarily essential to means provided by aspects of the invention.

[0021]FIG. 1 shows an exemplary configuration of a reservoir computing system 100. The reservoir computing system 100 may be an apparatus that performs learning based on input data, output data, and training data. Furthermore, the reservoir computing system 100 may be operable to perform testing and make predictions for output data corresponding to the input data, based on the learning results. The reservoir computing system 100 adjusts weights in the system, in a manner to reduce the difference between output data that is output in response to the input data and training data corresponding to the input data. The reservoir computing system 100 includes a data generator 110, an input layer 120, a r