Dynamic neural units in the control of linear and nonlinear systems

The performance evaluation of a dynamic neural unit (DNU) in the control of linear and nonlinear dynamical systems is described. The architecture of the dynamic neural unit embodies feedforward and feedback flow of signals weighted by the synaptic weights in a dynamical structure. Because of the dynamical nature of the neuron, it can be trained to learn and control unknown linear dynamical systems. Nonlinear functions can be approximated using multistage dynamic neural units, and hence can be trained to control nonlinear dynamical systems. The DNUs not only emulate, to some extent, the learning and control actions of the biological neurons, but also have the potential of a parallel-distributed intelligent control scheme for a large-scale complex dynamic system