Stable neural control of discrete systems

The control of nonlinear discrete systems using neural networks is discussed. The discrete systems discussed have the form y_{k + 1} = b(y_k,...,y_k-1)u_k + f(y_k,...y_k-1). Neural networks could be either radial basis functions (RBFs) or cerebellar model articulation controller (CMAC). The stability features are guaranteed, i.e., the errors between the desired values and the actual values are bounded. Theoretical results are strictly proved, and an example is used to explain the theoretical results