A novel method to solve inverse variational inequality problems based on neural networks

This paper presents a neural network for solving the inverse variational inequality problems. The proposed neural network possesses a simple one-layer structure and is suitable for parallel implementation. It is shown that the proposed neural networks are globally convergent to the optimal solution of the inverse variational inequality and are globally asymptotically stable, and globally exponentially stable, respectively under different conditions. Numerical examples are provided to illustrate the effectiveness and satisfactory performance of the neural networks.