We show that adaptive inverse control is a further member of the class of control design techniques with an internal model control structure. By implication, therefore, adaptive inverse control is supported by the firm analytical foundation on which internal model control is now based. In a further contribution, we present artificial neural network architectures for the implementation ofnon-linearinternal model control. This approach can be viewed as a non-linear analogue of adaptive inverse control; the network models used are nothing more than non-linear adaptive filters. We use two separate networks in the implementation of non-linear IMC; one network models the plant, and the second network models the plant inverse. We conclude with a simulation example demonstrating non-linear IMC using neural networks.