A new N-parallel updating method of the Hopfield-type neural network for N-queens problem

In the previous N-parallel updating methods of the Hopfield-type neural network for N-queens problem, N/spl times/N neurons have been grouped into N groups. Each group composed of N neurons which are located in a same horizontal line (column) or in a same diagonal line. However, these method did not give convergence results of 100% in all size of N. Also, they required a large convergence time steps. In our work, we propose a new N-parallel updating method of the Hopfield-type neural network for N-queens problem, in which, a new grouping method for N neurons composed in the same group has been adopted. As a result, simulation results of the proposed method show a best performance than the previous generally.