Reservoir computing uses a variety of physical, biologcal or computational processes to increase the non-linear diversity of input data the outputs of whih can then be used as inputs for a simpler final machine learning stage.. For example, input data might be used to drive electrical impolses into a semi-chaotic silicon substrate and the output currents measured at multiple points.
Used on pages 124, 145, 381, 574
Reservoir computing -- main stages