An efficient approach of the SOM algorithm to the traveling salesman problem

This paper presents an approach to the well-known traveling salesman problem (TSP) via competitive neural networks. The neural network model adopted in this work is the Kohonen network or self-organizing maps (SOM), which has important topological information about its neurons configuration. This paper is concerned with the initialization aspects, parameters adaptation, and the complexity analysis of the proposed algorithm. The modified SOM algorithm proposed in this paper has shown better results when compared with others neural network based approaches to the TSP.