Abstract
Combinatorial optimization seems to be a harsh field for Artificial Neural Networks (ANN), and in particular the Traveling Salesman Problem (TSP) is an exemplar benchmark where ANN today are not competitive with the best heuristics from the operations research literature. The thesis upheld in this work is that the Self-Organizing feature Map (SOM) paradigm can be an effective solving method for the TSP, if combined with appropriate mechanisms improving the efficiency and the accuracy. An original TSP-solver based on the SOM is tested over the largest TSP benchmarks, on which other ANN typically fail.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
B. Angéniol, G. de la C. Vaubois, and J-Y L. Texier. Self-organizing feature maps and the travelling salesman Problem. Networks 1:289–293, 1988.
D. Applegate, W. Cook, and A. Rhoe. Chained Lin Kernighan for large travelling salesman problems. Technical report, Rice University, 2000.
N. Aras, B. J. Oommen, and I. K. Altinel. The Kohonen network incorporating explicit statistics and its application to the traveling salesman problem. Neural Networks 12:1273–1284, 1999.
L. Burke. Conscientious neural nets for tour construction in the traveling salesman problem: the vigilant net. Computers and Operations Research, 23(2):121–129, 1996.
R. Durbin and D. Willshaw. An analogue approach to the travelling salesman problem using an elastic net method. Nature, 326:689–691, 1987.
J. J. Hopfield and D. Tank. Neural computation of decisions in optimization problems. Biological Cybernetics, 4:141–152, 1985.
T. Kohonen. Self-Organizing Maps. Springer-Verlag, Berlin, 1995.
S. Noel and H. Szu. Multiple-resolution divide and conquer neural networks for large-scale tsp-like energy minimization problems. In Proc Intern. Conference on Neural Networks pages 1278–1283, 1997.
A. Plebe and A.M. Anile. A neural-network-based approach to the double traveling salesman problem. Neural Computation, 14(2):437–471, 2001.
J. Y. Potvin. The travelling salesman problem: a neural network perspective. ORSA Journal on Computing, 5:328–348, 1993.
M. Recte, J.C. Taylor, A. Plebe, and G. Tropiano. Vision and neural control for an orange harvesting robot. In Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing, Venice, Italy, 1996.
G. Reinelt. Tsplib-a traveling salesman problem library. ORSA Journal on Computing, 3:376–384, 1991.
G. Reinelt. The Traveling Salesman. Springer-Verlag, Berlin, 1994.
K. Smith. An argument for abandoning the traveling salesman problem as a neural-network benchmark. IEEE Transactions on Neural Network, 7(6):1542–1544, 1996.
K. Smith. Neural networks for combinatorial optimization: a review of more than a decade of research. INFORMS Journal fo Computing, 11:15–33, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Plebe, A. (2002). An Effective Traveling Salesman Problem Solver Based on Self-Organizing Map. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_147
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_147
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive