Neural network for blind source separation

In this paper, we construct a neural network basing on smoothing approximation techniques and steepest descent method to solve a kind of blind source separation problem. Neural network can be implemented by circuits and is seen as an important method for solving optimization problems, especially large scale problem. Smoothing approximation is an efficient technique for solving nonsmooth optimization problems. We combine these two techniques to overcome the difficulties of the choices of the step size in discrete algorithms and the item in the set-valued map of differential inclusion. In theory, the proposed network can converge to the optimal solution of the given problem. Furthermore, one numerical experiment shows the effectiveness of the proposed network in this paper