Reservoir computing uses a variety of physical, biologcal or computational processes to increase the non-linear diversity of input data the outputs of which (called the readout) can then be used as inputs for a simpler final machine learning stage. For example, input data might be used to drive electrical impulses into a semi-chaotic silicon substrate and the output currents measured at multiple points.
Defined on pages 37, 145
Used on Chap. 1: page 6; Chap. 3: page 37; Chap. 6: page 124; Chap. 7: pages 145, 146, 147; Chap. 16: page 387; Chap. 24: page 584
Reservoir computing -- main stages