Neural learning for adaptive internal model control

This work describes how artificial neural networks can be applied in an adaptive control context. An attempt is made to merge conventional adaptive control concepts with today's neural way of thinking. Thus it is possible to throw light on some obvious links often remaining unnoticed. Special emphasis is put on the learning behavior of the network. Two learning rules are analyzed and tested in a simple example in the sequel. The well-known Widrow-Hoff rule is brought face to face with the recursive formulation of the least squares algorithm, a standard tool in adaptive control. This comparison leads to an increased understanding of learning properties and a critical evaluation of neural learning capabilities.