Mathematical analysis of some neural networks for solving linear and quadratic programming

Artificial neural network techniques have been introduced into the area of optimization in the last decade. Some neural network models have been suggested to solve linear and quadratic programming programs. The Kennedy and Chua model is one of these networks. In this paper results about the convergence of the model are obtained. Another related problem is how to choose a parameter value &smacr; so that the equilibrium point of the network immediately and properly approximates the original solution. Such an estimation for the parameter is given in a closed form when the network is used to solve linear programming.