A critique of neural networks for discrete-time linear control
Warwick, K. (1995) A critique of neural networks for discrete-time linear control. International Journal of Control, 61 (6). pp. 1253-1264. ISSN 0020-7179
Full text not archived in this repository.
To link to this article DOI: 10.1080/00207179508921955
This paper discusses the use of multi-layer perceptron networks for linear or linearizable, adaptive feedback.control schemes in a discrete-time environment. A close look is taken at the model structure selected and the extent of the resulting parametrization. A comparison is made 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.
Centaur Editors: Update this record