The co-adaptive neural network approach to the Euclidean Travelling Salesman Problem

Abstract

In this paper we consider the Euclidean Travelling Salesman Problem (ETSP). This is the problem of finding the shortest tour around a number of cities where the cities correspond to points in the Euclidean plane and the distances between cities are given by the usual Euclidean distance metric. We present a review of the literature with respect to neural network (NN) approaches for the ETSP, and the computational results that have been reported. Based upon this review we highlight two areas that are, in our judgement, currently neglected/lacking in the literature. These are: failure to make significant use of publicly available ETSP test problems in computational work, failure to address co-operation between neurons. Drawing upon our literature survey this paper presents a new Self-Organising NN approach, called the Co-Adaptive Net, which involves not just unsupervised learning to train neurons, but also allows neurons to co-operate and compete amongst themselves depending on their situation. Our Co-Adaptive Net algorithm also includes a number of algorithmic mechanisms that, based upon our literature review, we consider to have contributed to the computational success of previous algorithms. Results for 91 publicly available standard ETSP's are presented in this paper. The largest of these problems involves 85,900 cities. This paper presents: the most extensive computational evaluation of any NN approach on publicly available ETSP test problems that has been made to date in the literature, a NN approach that performs better, with respect to solution quality and/or computation time, than other NN approaches given previously in the literature. Drawing upon computational results produced as a result of the DIMACS TSP Challenge, we highlight the fact that none of the current NN approaches for the ETSP can compete with state of the art Operations Research heuristics. We discuss why we consider continuing to study and develop NN approaches for the ETSP to be of value.