How to Generate the Input Current for Exciting a Spiking Neural Model Using the Cuckoo Search Algorithm

  • Roberto A. Vazquez
  • Guillermo Sandoval
  • Jose Ambrosio
Part of the Studies in Computational Intelligence book series (SCI, volume 516)


Spiking neurons are neural models that try to simulate the behavior of biological neurons. This model generates a response (spikes or spike train) only when the model reaches a specific threshold. This response could be coded into a firing rate and perform a pattern classification task according to the firing rate generated with the input current. However, the input current must be carefully computed to obtain the desired behavior. In this paper, we describe how the Cuckoo Search algorithm can be used to train a spiking neuron and determine the best way to compute the input current for solving a pattern classification task. The accuracy of the methodology is tested using several pattern recognition problems.


Cuckoo Search Algorithm Spiking Neural Networks Pattern recognition 



The authors would like to thank CONACYT-INEGI and Universidad La Salle for the economical support under grant number 187637 and I-061/12, respectively.


  1. 1.
    A chaos synchronization-based dynamic vision model for image segmentation. 5, (2005)Google Scholar
  2. 2.
    Exploration of rank order coding with spiking neural networks for speech recognition. 4, (2005)Google Scholar
  3. 3.
    Abdull Hamed, H.N., Kasabov, N., Michlovský, Z., and Shamsuddin, S.M.: String pattern recognition using evolving spiking neural networks and quantum inspired particle swarm optimization. In: Proceedings of the 16th International Conference on Neural Information Processing. Part II, ICONIP ’09, LNCS, pp. 611–619. Springer-Verlag, Heidelberg (2009)Google Scholar
  4. 4.
    Balasubramanian, S., Panigrahi, S., Logue, C., Gu, H., Marchello, M.: Neural networks-integrated metal oxide-based artificial olfactory system for meat spoilage identification. J. Food Eng. 91(1), 91–98 (2009)Google Scholar
  5. 5.
    Baldwin, E.A., Bai, J., Plotto, A., Dea, S.: Electronic noses and tongues. Applications for the food and pharmaceutical industries. Sensors 11(5), 4744–4766 (2011)Google Scholar
  6. 6.
    Barthelemy, P., Bertolotti, J., Wiersma, D.S.: A levy flight for light. Nature 453, 495–498 (2008)Google Scholar
  7. 7.
    Belatreche, A., Maguire, L.P., and McGinnity, T.M.: Pattern recognition with spiking neural networks and dynamic synapse. In: International FLINS Conference on Applied Computational Intelligence, pp. 205–210 (2004)Google Scholar
  8. 8.
    Bermak, A., Martinez, D.: A compact 3d vlsi classifier using bagging threshold network ensembles. IEEE Trans. Neural Netw., 14(5), 1097–1109 (2003)Google Scholar
  9. 9.
    Bohte, S.M., Kok, J.N., Poutre, H.L.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1–4), 17–37 (2002)CrossRefMATHGoogle Scholar
  10. 10.
    Chen, H.T., Ng, K.T., Bermak, A., Law, M., Martinez, D.: Spike latency coding in biologically inspired microelectronic nose. IEEE Trans. Biomed. Circ. Syst., 5(2), 160–168 (2011)Google Scholar
  11. 11.
    Devroye, L., Györfi, L., Lugosi, G.: A probabilistic theory of pattern recognition. Springer, Heidelberg (1996)Google Scholar
  12. 12.
    Di Paolo, E.: Spike-timing dependent plasticity for evolved robots. Adapt. Behav., 10, 243–263 (2002)Google Scholar
  13. 13.
    Floreano, D., Zufferey, J.-C., Nicoud, J.-D.: From wheels to wings with evolutionary spiking neurons. Artif. Life, 11(1–2), 121–138 (2005)Google Scholar
  14. 14.
    Fu, J., Li, G., Qin, Y., Freeman, W.J.: A pattern recognition method for electronic noses based on an olfactory neural network. Sens. Actuators B: Chemical, 125(2), 489–497 (2007)Google Scholar
  15. 15.
    Garro, B., Sossa, H., and Vazquez, R.: Design of artificial neural networks using a modified particle swarm optimization algorithm. In: International Joint Conference on Neural Networks. IJCNN, pp. 938–945 (2009)Google Scholar
  16. 16.
    Garro, B.A., Sossa, H., and Vázquez, R.A.: Design of artificial neural networks using differential evolution algorithm. In: Proceedings of the 17th International Conference on Neural Information Processing: models and applications, Vol. Part II, pp. 201–208, ICONIP’10, LNCS, Springer-Verlag, Heidelberg (2010)Google Scholar
  17. 17.
    Gerstner, W., Kistler, W.M.: Spiking Neuron Models. Single Neurons, Populations. Cambridge University Press, Plasticity (2002)Google Scholar
  18. 18.
    Gomez-Chova, L., Calpe, J., Camps-Valls, G., Martin, J., Soria, E., Vila, J., Alonso-Chorda, L., Moreno, J.: Feature selection of hyperspectral data through local correlation and sffs for crop classification. In: Geoscience and Remote Sensing Symposium. IGARSS ’03. Proceedings. IEEE, International, vol. 1, pp. 555–557 (2003)Google Scholar
  19. 19.
    Haralick, R., Shanmugam, K., and Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern., SMC, 3(6): 610–621 (1973)Google Scholar
  20. 20.
    Hasselmo, M.E., Bodelón, C., Wyble, B.P.: A proposed function for hippocampal theta rhythm: separate phases of encoding and retrieval enhance reversal of prior learning. Neural Comput. 14, 793–817, April 2002Google Scholar
  21. 21.
    Hopfield, J.J., Brody, C.D.: What is a moment Cortical sensory integration over a brief interval. Proc. Natl. Acad. Sci., vol. 97 (25), 13919–13924, Dec 2000Google Scholar
  22. 22.
    Hu, M.-K.: Visual pattern recognition by moment invariants. IEEE Trans. Inform. Theory, 8(2), 179–187, Feb 1962Google Scholar
  23. 23.
    Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw., 14(6), 1569–1572, Nov 2003Google Scholar
  24. 24.
    Izhikevich, E.M.: Which model to use for cortical spiking neurons? IEEE Trans. Neural Netw., 15(5), 1063–1070, Sept 2004Google Scholar
  25. 25.
    Izhikevich, E.M.: Dynamical systems in neuroscience: the geometry of excitability and bursting. MIT Press, Computational Neurosci. (2007)Google Scholar
  26. 26.
    Jain, R., and Schunck, R.K.B.G.: Machine Vision. McGraw-Hill, New York (1995)Google Scholar
  27. 27.
    Karaboga, D., Akay, B., and Ozturk, C.: Artificial bee colony (abc) optimization algorithm for training feed-forward neural networks. In: Proceedings of the 4th International Conference on Modeling Decisions for Artificial Intelligence, MDAI ’07, LNCS, pp. 318–329, Springer-Verlag, Heidelberg (2007)Google Scholar
  28. 28.
    Karaboga, D., and Basturk, B.: Artificial bee colony (abc) optimization algorithm for solving constrained optimization problems. In: IFSA (1)’07, LNCS, pp. 789–798 (2007)Google Scholar
  29. 29.
    Kennedy, J., and Eberhart, R.: Particle swarm optimization. In: Proceedings. IEEE Int. Conf. Neural Netw. (1995) vol. 4, pp. 1942–1948, Aug 2002Google Scholar
  30. 30.
    Maass, W., Graz, T.U.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10, 1659–1671 (1997)Google Scholar
  31. 31.
    Murphy, P., Aha, D.: UCI Repository of machine learning databases. Technical report, University of California, Department of Information and Computer Science, Irvine, CA, USA (1994)Google Scholar
  32. 32.
    Nagy, G., Tolaba, J.: Nonsupervised crop classification through airborne multispectral observations. IBM J. Res. Dev. 16(2), 138–153 (1972)Google Scholar
  33. 33.
    Oh, E.H., Song, H.S., Park, T.H.: Recent advances in electronic and bioelectronic noses and their biomedical applications. Enzym. Microb. Tech. 48(67), 427–437 (2011)Google Scholar
  34. 34.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66, Jan 1979Google Scholar
  35. 35.
    Price, K.V., Storn, R.M., Lampinen, J.A.: Differential evolution a practical approach to global optimization. Nat. Comput. Ser. Springer-Verlag, Berlin (2005)Google Scholar
  36. 36.
    Schwenker, F., Kestler, H.A., Palm, G.: Three learning phases for radial-basis-function networks. Neural Netw. 14(45), 439–458 (2001)Google Scholar
  37. 37.
    Senthilnath, J., Omkar, S.N., Mani, V., and Karnwal, N.: Hierarchical artificial immune system for crop stage classification. In: Annuals IEEE India Conference (INDICON), pp. 1–4 (2011)Google Scholar
  38. 38.
    Thorpe, S.J., Guyonneau, R., Guilbaud, N., Allegraud, J.-M., and VanRullen R.: Spikenet: real-time visual processing with one spike per neuron. Neurocomputing, 58–60:857–864 (2004). (Comput. Neurosci.: Trends Res. 2004)Google Scholar
  39. 39.
    Vazquez, R.: Izhikevich neuron model and its application in pattern recognition. Aust. J. Intell. Inf. Process. Syst. 11(1), 35–40 (2010)Google Scholar
  40. 40.
    Vazquez, R.: A computational approach for modeling the biological olfactory system during an odor discrimination task using spiking neuron. BMC Neurosci. 12(Suppl 1), p. 360 (2011)Google Scholar
  41. 41.
    Vazquez, R.: Training spiking neural models using cuckoo search algorithm. In: IEEE Congress on Evolutionary Computation (CEC), pp. 679–686 (2011)Google Scholar
  42. 42.
    Vazquez, R., and Cacho andn, A.: Integrate and fire neurons and their application in pattern recognition. In: 7th International Conference on Electrical Engineering Computing Science Automatic Control (CCE), pp. 424–428 (2010)Google Scholar
  43. 43.
    Vazquez, R., Sossa, H., Garro, B.: 3d object recognition based on some aspects of the infant vision system and associative memory. Cognitive Comput. 2, 86–96 (2010)Google Scholar
  44. 44.
    Vázquez R.A.: Pattern recognition using spiking neurons and firing rates. In: Proceedings of the 12th Ibero-American Conference on Advances Artificial Intelligence, IBERAMIA’10, LNAI, pp. 423–432, Springer-Verlag, Heidelberg (2010)Google Scholar
  45. 45.
    Vázquez, R.A., and Garro, B.A.: Training spiking neurons by means of particle swarm optimization. In: Proceedings of the Second International Conference on Advances in Swarm Intelligence, vol. Part I, ICSI’11, pp. 242–249. Springer-Verlag, Heidelberg (2011)Google Scholar
  46. 46.
    Vazquez Espinoza De Los Monteros, R.A., and Sossa Azuela, J. H.: A new associative model with dynamical synapses. Neural Process. Lett., 28:189–207, Dec 2008Google Scholar
  47. 47.
    Viswanathan, G.M., Buldyrev, S.V., Havlin, S., da Luz, M.G.E., Raposo, E.P., Stanley, H.E.: Optimizing the success of random searches. Nature 401, 911–914 (1999)CrossRefGoogle Scholar
  48. 48.
    Yang, X.-S.: 1-optimization and metaheuristic algorithms in engineering. Metaheuristics in water, geotechnical and transport engineering, pp. 1–23. Elsevier, Oxford (2013)Google Scholar
  49. 49.
    Yang, X.-S., and Deb, S.: Cuckoo search via levy flights. In: World Congress on Nature Biologically Inspired Computing, NaBIC, pp. 210–214 (2009)Google Scholar
  50. 50.
    Yin, Y., Yu, H., Zhang, H.: A feature extraction method based on wavelet packet analysis for discrimination of chinese vinegars using a gas sensors array. Sens. Actuators B: Chemical 134(2), 1005–1009 (2008)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Roberto A. Vazquez
    • 1
  • Guillermo Sandoval
    • 1
  • Jose Ambrosio
    • 1
  1. 1.Intelligent Systems GroupUniversidad La SalleMexico CityMexico

Personalised recommendations