Delayed Lagrangian neural networks for solving convex programming problems

In this paper, the global convergence is further studied for the Lagrangian programming neural networks. A delayed Lagrangian programming neural network is proposed for solving a class of convex programming problems with equality constraints. Based on Lyapunov method, it is proved that the delayed Lagrangian networks are stable and globally convergent under some conditions. Simulation examples are provided to show that the Lagrangian networks with delay are more effective than that without delays by choosing proper delays.