A CRITIQUE OF NEURAL NETWORKS FOR DISCRETE-TIME LINEAR-CONTROL

This paper discusses the use of multi-layer perceptron networks for li near or linearizable, adaptive feedback control schemes in a discrete- time environment. A close look is taken at the model structure selecte d and the extent of the resulting parametrization. A comparison is mad e with standard, non-perceptron algorithms, e.g. self-tuning control, and it is shown how gross over-parametrization can occur in the neural network case. Because of the resultant heavy computational burden and poor controller convergence, a strong case is made against the use of neural networks for discrete-time linear control.