An Efficient Growing Ring SOM and Its Application to TSP
Yanping Bai, Wendong Zhang, Hongping Hu · 2006
Abstract:- This paper presents an automatic parameters adjustment learning algorithm for self-organizing maps having growing ring topology. Like the existing SOM-like algorithm, the heuristic algorithm possesses many of these advantages of a good heuristic for the TSP solution. These advantages are easy implementation, fast computation, and production of good solutions. Computer programs developed in MATLAB for the heuristic algorithm were used to solve twelve test problems of the TSP from the TSPLIB. The experiment is showed that the results have an average of 2.4925 % difference from the optimum route. We can find almost optimal route by the heuristic algorithm. The algorithm is well suited for larger instances of the TSP since it has a fast convergence and low complexity. Key-Words:- Neural networks; Self-organizing maps; Traveling salesman problem; Combinatorial optimization; Neural computation 1