On the self-feedback controlled chaotic neural network and its application to N-Queen problem

To overcome the problem that a chaotic neural network (CNN) cannot escape from a local minimal point, a self-feedback controlled CNN is proposed. The proposed system can perceive to be caught in a local minimal point and can escape from it by reinforcing its own self-feedback connection autonomously. To confirm the effectiveness of the proposed system, it is applied to the N-Queen problem N=50, 100 and 200. From experimental results the success rate to obtain a solution is improved from 84.9% to 98.8% in N=200