Solving nonlinear complementarity problems with neural networks: A reformulation method approach (Q5939878)

The authors present a neural network approach for solving nonlinear complementarity problems. The neural network model is derived from an unconstrained minimization reformulation of the complementarity problem. Existence and convergence of the trajectory of the neural network are addressed in detail. In addition, stability in the sense of Lyapunov, asymptotic stability and exponential stability are explored for the neural network model. The theory developed here is also valid for neural network models derived from a number of reformulation methods for nonlinear complementarity problems. Simulation results are given.