Neural network adaptive controllers

The application of parallel distributed processing (neural networks) to the problem of adaptive control is examined. Focusing on the backpropagation paradigm, a general form of a controller consistent with neural networks is developed and combined with linear least-squares parameter-estimation techniques to suggest a structure for neural network adaptive controllers. This neural network adaptive control structure is then applied to a number of estimation problems using the longitudinal motion of the A-4 aircraft as a model