Abstract
In this Letter we show that discrete multivalued Hopfield-type neural networks enable a relatively easy formulation of the Traveling Salesman Problem compared to the traditional Hopfield model. Thus, with the multivalued representation the network can be easily confined to feasible solutions, avoiding the need to tune any parameter. An investigation into the performance of the network has led us to define updating rules based on simple effective heuristic algorithms, a technique that can not be usually incorporated into standard Hopfield models. Simulation results for Euclidean Traveling Salesman Problems taken from the data library TSPLIB [11] indicate that this multivalued neural approach is superior to the best neural network currently reported for this problem.
Similar content being viewed by others
References
Hopceld, J. J. and Tank, D. W.: Neural computation of decisions in optimization problems, Biol. Cybern. 52 (1985), 141–152.
Hopceld, J. J.: Neural Networks and physical systems with emergent collective computational abilities, Proc. Ac. Academy Sci. USA 79 (1982), 2554–2558.
Hopceld, J. J.: Neurons with graded response have collective computational properties like those of two-state neurons, Proc. Ac. Academy Sci. USA 81 (1984), 3088–3092.
Glesner, M. and Pöchmüller, W.: Neurocomputers-An overview of neural Networks in VLSI. London: Chapman and Hall, 1994.
Shams, S. and Gaudiot, J. L.: Implementing regularly structured neural networks on the DREAM machine, IEEE Trans. Neural Networks 6 (1995), 407–421.
Farhat, N. H., Psaltis, D., Prata, A. and Peak, E.: Optical implementation of the Hopceld model, Appl. Opt. 4 (1985), 1469–1475.
Lawler, E. L., Lenstra, J. K., Rinnooy Kan, A. H. G. and Shmoys, D. B.: The traveling salesman problem, New York: Wiley, 1985.
Reeves, C. R.: Modern heuristic techniques for combinatorial problems, Oxford: Blackwell, 1993.
Garey, M. R. and Johnson, D. S.: Computers and Intractability: A Guide to the theory of NP-Completeness, New York: W. H. Freeman, 1979.
Lin, S. and Kernighan, B.: An effective heuristic algorithm for the traveling salesman problem, Operations Research 21 (1973), 498–516.
Reinelt, G.: TSPLIB-a travelling salesman problem library, ORSA Journal on Computing 3 (1991), 376–384.
Reinelt, G.: The travelling salesman. Computational solutions for TSP applications, Berlin: Springer, 1994.
Aras, N., Oomen, B. J. and Altinel, I. K.: The Kohonen network incorporating explicit statistics and its application to the travelling salesman problem, Neural Networks 12 (1999), 1273–1284.
Burke, L. I. and Damany, P.: The guilty net for the travelling salesman problem, Computers and Operations Research 19 (1992), 255–265.
Kohonen, T.: Self-organizing maps, Berlin: Springer, 1995.
Gee, A. H. and Prager, R. W.: Polyhedral combinatorics and neural networks, Neural Computation 6(1) (1994), 161–180.
Smith, K.: An argument for abandoning the traveling salesman problem as a neuralnetwork benchmark, IEEE Trans on Neural Networks 7(6) (1996), 1542–1544.
Wilson, V. and Pawley, G. S.: On the stability of the TSP problem algorithm of Hopceld and Tank, Biological Cybernetics 58 (1988), 63–70.
Erdem, M. and Ozturk, Y.: A New Family of Multivalued Networks, Neural Networks 9(6) (1996), 979–989.
Peng, M., Gupta, N. K. and Armitage, A. A. F.: An investigation into the Improvement of Local Minima of the Hopceld Network, Neural Networks 9(7) (1996), 1241–1253.
Li, S. Z.: Improving Convergence and Solution Quality of Hopceld-Type Neural Networks with Augmented LagrangeMultipliers, IEEE Trans. on Neural Networks 7(6) (1996), 1507–1516.
Martín-Valdivia, M., Ruiz-Sepúlveda, A. and Triguero-Ruiz, F.: Improving local minima of Hopceld networks with augmented Lagrange multipliers for large scale TSPs, Neural Networks 13 (2000), 283–285.
Zeng, X. and Martinez, T.: A New Relaxation Procedure in the Hopceld Network for solving Optimization Problems, Neural Processing Letters 10 (1999), 211–222.
Johnson, D. S. and McGeoh, L. A.: The Traveling Salesman Problem: A Case Study in Local Optimization, In: E. H. Aarts and J. K. Lenstra (eds.), Local Search in Combinatorial Optimization, John Wiley and Sons: London, 1997, pp. 215–310.
Kirkpatrick, S.: Optimization by simulated annealing: Quantitative studies, J. Stat. Physics 34 (1984), 976-986.
Kirkpatrick, S., Gelatt, C. D. and Vecchi, M. P.: Optimization by Simulated Annealing, Science 220 (1983), 671–680.
Cerny, V.: A Thermodynamical Approach to the Travelling Salesman Problem: An Efccient Simulation Algorithm, J. Optimization Theory and Appl. 45 (1985), 41–51.
Croes, G. A.: A method for solving traveling salesman problems, Operations Research 6 (1958) 791–812.
Glover, F.: Future paths for integer programming and links to articcial intelligence, Computers & Ops. Res. 13 (1986), 533–549.
Mehta, S. and Fulop, L.: An analog Neural Network to Solve the Hamiltonian Cycle Problem, Neural Networks 6 (1993), 869–881.
Angéniol, B., Vaubois, G. and Texier, J.: Self-organizing feature maps and the Traveling Salesman problem, Neural Networks 1 (1988), 289–283.
Durbin, R. and Willshaw, D.: An analogue approach to the Traveling Salesman Problem using an elastic net method, Nature 326 (1987), 689–691.
Xu, X. and Tsai, W. T.: Effective neural algorithms for the travelling salesman problem, Neural Networks 4 (1991), 193–205.
Galán-Marín, G. and Muñoz-Pérez, J.: Design and Analysis of Maximum Hopceld Networks, IEEE Trans. on Neural Networks 12(2) (2001), 1–11.
Galán-Marín, G. and Muñoz-Pérez, J.: A new input-output function for binary Hopceld Neural Networks, Lecture Notes in Computer Science, Foundations and Tools for Neural Modeling, Springer Verlag, Berlin, (1999) vol. 1606, pp. 311–320.
Galán-Marín, G. and Muñoz-Pérez, J.: Design of a Neural Network for solving the Four-Color-Map Problem, Iberoamerican Journal of Artificial Intelligence 8 (1999), 6–17, (In Spanish).
Galán-Marín, G.: Recurrent Neural Networks for Combinatorial Optimization, Ph.D. dissertation, University of Málaga, Málaga, Spain, 2000 (In Spanish).
Galán-Marín, G. and Muñoz-Pérez, J.: Finding Near-Maximum Cliques with Competitive Hopceld Networks, Proc. of International ICSC Symposium on Neural Computation, Berlin, Germany (2000), pp. 62–69.
Mérida-Casermeiro, E.: Recurrent Multivalued Neural Networks for Combinatorial Optimization and Pattern Recognition, Ph.D. dissertation, University of Málaga, Málaga, Spain, 2000 (In Spanish).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Mérida-Casermeiro, E., Galán-Marín, G. & Muñoz-Pérez, J. An Efficient Multivalued Hopfield Network for the Traveling Salesman Problem. Neural Processing Letters 14, 203–216 (2001). https://doi.org/10.1023/A:1012751230791
Issue Date:
DOI: https://doi.org/10.1023/A:1012751230791