A projection based recurrent neural network approach to compute the distance between a point and an ellipsoid with box constraint

Here we proposed a projection based recurrent neural network for computing the distance between a point and an ellipsoid subject to box constraint. The proposed neural network makes use of a cost gradient projection onto the tangent space of the constraints and the well-known projection theorem. It can be proved that the neural network is stable. And the ability of globally converging to optimal solution within a finite time is also guaranteed. Global convergence analysis is established for nonconvex-constrained optimization problems. Numerical simulation is performed to illustrated the performance of this recurrent neural network model proposed.