Comments on "Robustifying nonlinear systems using high-order neural network controllers"

*** PLEASE ASK ME ABOUT THIS (PHILIP) *** In the original paper by G.A. Rovithakis (ibid., vol.44, p.102-8, 1999), a nonlinear dynamical system is considered. The author indicates that Rovithakis overlooked some essential assumptions on the allowable perturbations, that the problem is therefore not well-posed, and that the controller derived is incorrect Rovithakis replies that it is well known that a system of the type considered can in some cases be decomposed into a controllable and an uncontrollable part and that it is obvious that in such a case the controller would apply only to the former. Rovithakis shows that Zhang's other results are incorrect.