Numerical solution for linear and quadratic programming problems using a recurrent neural network

A recurrent neural network is proposed in this paper for solving linear and quadratic programming problems. The main advantage of this network is that here we are not in need of parameters setting. Moreover, using this network we can solve primal programming problems and their duals simultaneously. We prove the global convergence of the neural network and demonstrate the advanced performance of the proposed network by means of simulation of several numerical examples.