A high order neural network to solve N-queens problem

High order hopfield network has a higher store capacity and a faster convergence speed compared with the first order hopfield network. However, in optimization field, such as combination optimization field, high order network is seldom to be used. So how to construct high order network to solve these problem is an interesting problem. In this paper a new kind of high order discrete hopfield neural network is proposed to solve N-queens problem. The construction method of energy function is given and the neural computing method is shown. It is also discussed the method how to speed the convergence and escape from local minima. Compared with the first order hopfield network, experimental results show high order network has a quick convergence speed, the performance of high order network is better than the discrete Hopfield network.