Application of neural network to hierarchical optimal control of the class of continuous time-varying large-scale systems

We present a method for applying a neural network to the hierarchical control problem of a class of continuous time varying large scale systems. We assume that the continuous time system is linear time varying, and disturbed by additive white noises, that the state information at the sampling instants is incomplete, and that the continuous time criteria are quadratic. A two level connectional network of novel architecture is designed for the optimal control problem of large scale systems. Circuits to solve these problems are designed using general principles.