An Effective Solution to Large-scale Traveling Salesman Problems Using Chaotic Neural Networks

This paper presents an effective TSP (Traveling Salesman Problem) solver for large-scale problems using neural networks. Firstly, in the proposed method, an intractable large-scale TSP is divided into some tractable small-scale problems (clusters) using a clustering technique. Secondly, a visiting order of clusters is determined using chaotic neural networks (CNNs). Thirdly, the small-scale problems are solved using CNNs. Simultaneously, two pairs of connecting cities between adjacent clusters are also determined using CNNs. Through computer simulations, it is confirmed that the proposed method is effective to solve the large-scale problems.