... and ˜yµ,j(0) = 0, for all j 0. The form of the equation is,moreover, a convex mixture. The choice of µ controls the trade-off between depth andresolution; small µ provides low-depth and high-resolution ... ,q.A taxonomy of recurrent neural networks architectures is presented by Tsoi and Back(1997). The choice of structure depends upon the dynamics of the signal, learningalgorithm and ultimately the ... 1), ˆy(k − 1)), (3.27)where ϕ and Ψ represent general classes of nonlinearities. The particular choice ofN minimal state variables is not unique, therefore several canonical forms8exist.A...