Multilayer feedforward networks are universal approximators
Neural Networks
Nonlinear control systems: an introduction (2nd ed.)
Nonlinear control systems: an introduction (2nd ed.)
Hi-index | 0.00 |
A special model of artificial neural networks has been developed for the purpose of output tracking of a class of nonlinear systems and an original training structure basing on the error back-propagation algorithm is introduced. This approach which, on the ground of input-output observations, turns feasible the use of inverse control techniques appears much simpler than other existing neural control approaches for inverse control problem. Simulation results reveal that the proposed approach presents rapid training and good tracking performances.