Inversion of recurrent neural networks for control of non-linear systems

Recurrent neural networks can be used for both the identification and control of non-linear systems. This paper takes a previously derived set of theoretical results about recurrent neural networks and applies them to task of providing internal model control for a non-linear plant. Using the theoretical results, we show how an inverse controller can be produced from a neural network model of the plant, without the need to train an additional network to perform the inverse control.