Improvement of Hopfield neural network algorithm

This paper presents an improved algorithm based on Hopfield neural network, describes how to achieve TSP problem solution. And after the analysis of the method deficiencies, it respectively improves the existing algorithm in parameter setting and energy functions, and proposes further improvements for the algorithm according to the phenomenon of repeat solutions. Finally, it gives the results of the improved algorithm. The experimental results show that the improved algorithm can greatly improve the solving speed and convergence rate.