Relaxation of coefficient sensitiveness to performance for neural networksusing neuron filter through total coloring problems

In this paper we show that the neuron filter is effective for relaxing the coefficient sensitiveness of the Hopfield neural network for combinatorial optimization problems. Since the parameters in motion equation have a signi ficant influence on the performance of the neural network, many studies hav e been carried out to support determining the value of the parameters. Howe ver, not a few researchers have determined the value of the parameters expe rimentally yet. We show that the use of the neuron filter is effective for the parameter tuning, particularly for determining their values experimenta lly through simulations.