Skip to main content
SpringerLink
Log in

Parameter tuning of continuous Hopfield network applied to combinatorial optimization

  • Published:
Annals of Mathematics and Artificial Intelligence Aims and scope Submit manuscript

Abstract

The continuous Hopfield network (CHN) has provided a powerful approach to optimization problems and has shown good performance in different domains. However, two primary challenges still remain for this network: defining appropriate parameters and hyperparameters. In this study, our objective is to address these challenges and achieve optimal solutions for combinatorial optimization problems, thereby improving the overall performance of the continuous Hopfield network. To accomplish this, we propose a new technique for tuning the parameters of the CHN by considering its stability. To evaluate our approach, three well-known combinatorial optimization problems, namely, weighted constraint satisfaction problems, task assignment problems, and the traveling salesman problem, were employed. The experiments demonstrate that the proposed approach offers several advantages for CHN parameter tuning and the selection of optimal hyperparameter combinations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Data Availability

The data sets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

References

  1. Wen, U.P., Lan, K.M., Shih, H.S.: A review of Hopfield neural networks for solving mathematical programming problems. Eur. J. Oper. Res. 198(3), 675–687 (2009)

    Article  MathSciNet  Google Scholar 

  2. Talaván, P.M., Yáñez, J.: The graph coloring problem: A neuronal network approach. Eur. J. Oper. Res. 191(1), 100–111 (2008)

    Article  MathSciNet  Google Scholar 

  3. Talaván, P.M., Yáñez, J.: A continuous Hopfield network equilibrium points algorithm. Comput. Oper. Res. 32(8), 2179–2196 (2005)

    Article  MathSciNet  Google Scholar 

  4. Haddouch, K., Elmoutaoukil, K., Ettaouil, M.: Solving the weighted constraint satisfaction problems via the neural network approach. Int. J. Interact. Multim. Artif. Intell. 4(1), 56–60 (2016)

    Google Scholar 

  5. Hoffman, K.L., Padberg, M., Rinaldi, G.: Traveling salesman problem. Encycl. Oper. Res. Manag. Sci. 1, 1573–1578 (2013)

    Google Scholar 

  6. Ettaouil, M., Loqman, C., Hami, Y., Haddouch, K.: Task assignment problem solved by continuous hopfield network. Int. J. Comput. Sci. Issues (IJCSI) 9(2), 206 (2012)

    Google Scholar 

  7. Lecoutre, C., Paris, N., Roussel, O., Tabary, S.: Solving WCSP by extraction of minimal unsatisfiable cores. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, pp. 915-922. IEEE, (2013)

  8. Arora, R.K., Rana, S.P.: Heuristic algorithms for process assignment in distributed computing systems. Inf. Process. Lett. 11(4–5), 199–203 (1980)

    Article  Google Scholar 

  9. de la Vega, W.F., Lamari, M.: The task allocation problem with constant communication. Discret. Appl. Math. 131(1), 169–177 (2003)

    Article  MathSciNet  Google Scholar 

  10. Roupin, F.: On approximating the memory-constrained module allocation problem. Inf. Process. Lett. 61(4), 205–208 (1997)

    Article  MathSciNet  Google Scholar 

  11. Haddouch, K., El Moutaouakil, K.: New Starting Point of the Continuous Hopfield Network. In: International Conference on Big Data. Cloud and Applications, pp. 379–389. Springer, Cham (2018)

  12. Ullman, J.D.: NP-complete scheduling problems. J. Comput. Syst. Sci. 10(3), 384–393 (1975)

    Article  MathSciNet  Google Scholar 

  13. Rbihou, S., Haddouch, K.: Comparative study between a neural network, approach metaheuristic and exact method for solving traveling salesman problem. In: 2021 Fifth International Conference On Intelligent Computing in Data Sciences (ICDS), pp. 1–5. IEEE, (2021)

  14. Hopfield, J.J., Tank, D.W.: “Neural’’ computation of decisions in optimization problems. Biol. Cybern. 52(3), 141–152 (1985)

    Article  Google Scholar 

  15. Lecoutre, instances aviable at: http://www.cril.univ-artois.fr/~lecoutre/benchmarks.html (2008)

  16. Reinelt, G.: TSPLIB–A traveling salesman problem library. ORSA J. Comput 3(4), 376–384 (1991)

    Article  Google Scholar 

  17. Elloumi, S.: The task assignment problem, a library of instances. (2004)

  18. Bousoño-Calzón, C., Salcedo-Sanz, S.: A discrete-time quantizedstate Hopfield neural network. Ann. Math. Artif. Intell. 42(4), 345–367 (2004)

    Article  MathSciNet  Google Scholar 

  19. El Alaoui, M., El Moutaouakil, K., Ettaouil, M.: A multi-step method to calculate the equilibrium point of the continuous hopfield networks: Application to the max-stable problem. Int. J. Comput. Sci. Inf. Secur. (IJCSIS) 14(6), 216–221 (2016)

    Google Scholar 

  20. Medsker, L.R., Jain, L.C.: Recurrent neural networks. Des. Appl. 5, 64–67 (2001)

    Google Scholar 

  21. Hopfield, J.J.: Hopfield network. Scholarpedia 2(5), 1977 (2007)

    Article  Google Scholar 

  22. Paik, J.K., Katsaggelos, A.K.: Image restoration using a modified Hopfield network. IEEE Trans. Image Process. 1(1), 49–63 (1992)

    Article  Google Scholar 

  23. Wang, Y., You, J.H., Lin, F., Yuan, L.Y., Zhang, M.: Weight constraint programs with evaluable functions. Ann. Math. Artif. Intell. 60(3), 341–380 (2010)

    Article  MathSciNet  Google Scholar 

  24. Khachay, M., Neznakhina, K.: Complexity and approximability of the Euclidean generalized traveling salesman problem in grid clusters. Ann. Math. Artif. Intell. 88(1), 53–69 (2020)

    Article  MathSciNet  Google Scholar 

  25. Talaván, P.M., Yáñez, J.: Parameter setting of the Hopfield network applied to TSP. Neural Netw. 15(3), 363–373 (2002)

    Article  Google Scholar 

  26. Wang, Q., Sun, X., Golden, B.L., Jia, J.: Using artificial neural networks to solve the orienteering problem. Ann. Oper. Res. 61(1), 111–120 (1995)

    Article  Google Scholar 

  27. Smith, K.A., Gupta, J.N.: Neural networks in business: techniques and applications for the operations researcher. Comput. Oper. Res. 27(11–12), 1023–1044 (2000)

    Article  Google Scholar 

  28. Smith, K., Palaniswami, M., Krishnamoorthy, M.: Traditional heuristic versus Hopfield neural network approaches to a car sequencing problem. Eur. J. Oper. Res. 93(2), 300–316 (1996)

    Article  Google Scholar 

  29. Talaván, P.M., Yáñez, J.: The generalized quadratic knapsack problem. A neuronal network approach. Neural Netw. 19(4), 416–428 (2006)

    Article  Google Scholar 

  30. Dieu, V.N., Ongsakul, W.: Hopfield lagrange network for economic load dispatch. In: Innovation in power, control, and optimization: Emerging energy technologies pp. 57–94. IGI Global, (2012)

  31. Walsh, M.P., O’malley, M.J.: Augmented Hopfield network for unit commitment and economic dispatch. IEEE Trans. Power. Syst. 12(4), 1765–1774 (1997)

  32. Ettaouil, M., Elmoutaouakil, K., Ghanou, Y.: The continuous hopfield networks (CHN) for the placement of the electronic circuits problem. WSEAS Trans. Comput. 8(12) (2009)

  33. Ahn, C.W., Ramakrishna, R.S., Kang, C.G., Choi, I.C.: Shortest path routing algorithm using hopfield neural network. Electron. Lett. 37(19), 1176–1178 (2001)

    Article  Google Scholar 

  34. Tan, K.C., Tang, H., Ge, S.S.: On parameter settings of Hopfield networks applied to traveling salesman problems. IEEE Trans. Circ. Syst. I Regul. Pap. 52(5), 994–1002 (2005)

    Article  MathSciNet  Google Scholar 

  35. Szu, H.: Fast TSP algorithm based on binary neuron output and analog neuron input using the zero-diagonal interconnect matrix and necessary and sufficient constraints of the permutation matrix. In: Proc. Int. Conf. on Neural Networks, pp. 259–266. San Diego, CA, 1988, (1988)

  36. Joudar, N.E., En-Naimani, Z., Ettaouil, M.: Using continuous Hopfield neural network for solving a new optimization architecture model of probabilistic self organizing map. Neurocomputing 344, 82–91 (2019)

    Article  Google Scholar 

  37. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79(8), 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  38. Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A learning algorithm for Boltzmann machines. Cogn. Sci. 9(1), 147–169 (1985)

    Google Scholar 

  39. Alenezi, F., Santosh, K.C.: Geometric regularized hopfield neural network for medical image enhancement. Int. J. Biomed. Imaging 2021, (2021)

  40. Lai, Q., Wan, Z., Zhang, H., Chen, G.: Design and analysis of multiscroll memristive hopfield neural network with adjustable memductance and application to image encryption. IEEE Trans. Neural Netw. Learn, Syst (2022)

  41. Wan, Q., Yan, Z., Li, F., Chen, S., Liu, J.: Complex dynamics in a Hopfield neural network under electromagnetic induction and electromagnetic radiation. Chaos Interdiscip. J. Nonlinear Sci. 32(7), 073107 (2022)

    Article  MathSciNet  Google Scholar 

  42. Xiao, Y., Zhang, Y., Dai, X., Yan, D.: Clustering Based on Continuous Hopfield Network. Mathematics 10(6), 944 (2022)

    Article  Google Scholar 

  43. Sun, J., Xiao, X., Yang, Q., Liu, P., Wang, Y.: Memristor-based Hopfield network circuit for recognition and sequencing application. AEU-Int. J. Electron. Commun. 134, 153698 (2021)

    Article  Google Scholar 

  44. Angelov, P.P., Soares, E.A., Jiang, R., Arnold, N.I., Atkinson, P.M.: Explainable artificial intelligence: an analytical review. Wiley Interdiscip. Rev. Data Min. Knowl. Disc. 11(5), e1424 (2021)

    Article  Google Scholar 

  45. Seidl, P., Renz, P., Dyubankova, N., Neves, P., Verhoeven, J., Wegner, J.K., Klambauer, G.: Improving few-and zero-shot reaction template prediction using modern hopfield networks. J. Chem. Inf. Model. 62(9), 2111–2120 (2022)

    Article  Google Scholar 

  46. Joudar, N.E., Ettaouil, M.: Mathematical mixed-integer programming for solving a new optimization model of selective image restoration: modelling and resolution by CHN and GA. Circ. Syst. Sig. Process. 38(5), 2072–2096 (2019)

    Article  MathSciNet  Google Scholar 

  47. Hartmanis, J.: Computers and intractability: a guide to the theory of np-completeness (Michael R. Garey and David S. Johnson). SIAM Rev. 24(1), 90 (1982)

  48. Billionnet, A., Costa, M.C., Sutter, A.: An efficient algorithm for a task allocation problem. J. ACM (JACM) 39(3), 502–518 (1992)

    Article  MathSciNet  Google Scholar 

  49. Kasihmuddin, M.S.M., Mansor, M.A., Sathasivam, S.: Hybrid genetic algorithm in the hopfield network for logic satisfiability problem. Pertanika J. Sci. Technol. 25(1) (2017)

  50. de la Vega, W.F., Lamari, M.: The task allocation problem with constant communication. Discret. Appl. Math. 131(1), 169–177 (2003)

    Article  MathSciNet  Google Scholar 

  51. Feng, G., Douligeris, C.: Using Hopfield networks to solve traveling salesman problems based on stable state analysis technique. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium Vol. 6, pp. 521-526. IEEE, (2000)

  52. Mérida-Casermeiro, E., Galán-Marín, G., Munoz-Perez, J.: An efficient multivalued Hopfield network for the traveling salesman problem. Neural Process. Lett. 14, 203–216 (2001)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Engineering, Systems and Applications, Sidi Mohamed Ben Abdellah University, Fez, Morocco

    Safae Rbihou & Khalid Haddouch

  2. Research Center STIS, M2CS, Department of Applied Mathematics and Informatics, ENSAM, Mohammed V University in Rabat, Rabat, Morocco

    Nour-Eddine Joudar

Authors
  1. Safae Rbihou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nour-Eddine Joudar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Khalid Haddouch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Safae Rbihou.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rbihou, S., Joudar, NE. & Haddouch, K. Parameter tuning of continuous Hopfield network applied to combinatorial optimization. Ann Math Artif Intell 92, 257–275 (2024). https://doi.org/10.1007/s10472-023-09895-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10472-023-09895-6

Keywords

Mathematics Subject Classification (2010)

Search

Navigation