A neural network controller is developed to learn the inverse dynamics
of unknown dynamic systems and to serve as a feedforward controller.
Artificial neural networks, which consist of a set of processing units
with interconnections between them, are used to get the desired outpu
t. The interconnections, known as weights, can be on-line tuned. Hence
the controller is adaptive in nature. Neural networks can be used to
represent the inverse dynamics of unknown dynamic systems. The error b
ack propagation technique is used in the learning process. The control
ler is intelligent enough to learn from its experience. The performanc
e of the intelligent controller for learning and control of dynamic sy
stems is very successful.