reservoir computing

Terms from Artificial Intelligence: humans at the heart of algorithms

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.

Used in Chap. 6: page 84; Chap. 7: pages 99, 100; Chap. 16: page 247; Chap. 24: page 376

Reservoir computing – main stages