Advertisement

Training Spiking Neurons by Means of Particle Swarm Optimization

  • Roberto A. Vázquez
  • Beatriz A. Garro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6728)

Abstract

Meta-heuristic algorithms inspired by nature have been used in a wide range of optimization problems. These types of algorithms have gained popularity in the field of artificial neural networks (ANN). On the other hand, spiking neural networks are a new type of ANN that simulates the behaviour of a biological neural network in a more realistic manner. Furthermore, these neural models have been applied to solve some pattern recognition problems. In this paper, it is proposed the use of the particle swarm optimization (PSO) algorithm to adjust the synaptic weights of a spiking neuron when it is applied to solve a pattern classification task. Given a set of input patterns belonging to K classes, each input pattern is transformed into an input signal. Then, the spiking neuron is stimulated during T ms and the firing rate is computed. After adjusting the synaptic weights of the neural model using the PSO algorithm, input patterns belonging to the same class will generate similar firing rates. On the contrary, input patterns belonging to other classes will generate firing rates different enough to discriminate among the classes. At last, a comparison between the PSO algorithm and a differential evolution algorithm is presented when the spiking neural model is applied to solve non-linear and real object recognition problems.

Keywords

Particle Swarm Optimization Particle Swarm Optimiza Algorithm Neuron Model Input Pattern Synaptic Weight 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Garro, B.A., Sossa, H., Vazquez, R.A.: Design of Artificial Neural Networks using a Modified Particle Swarm Optimization Algorithm. IJCNN, 938–945 (2009)Google Scholar
  2. 2.
    Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Networks 10(9), 1659–1671 (1997)CrossRefGoogle Scholar
  3. 3.
    Loiselle, S., Rouat, J., Pressnitzer, D., Thorpe, S.: Exploration of rank order coding with spiking neural networks for speech recognition. IJCNN 4, 2076–2080 (2005)Google Scholar
  4. 4.
    Thorpe, S.J., Guyonneau, R., et al.: SpikeNet: Real-time visual processing with one spike per neuron. Neurocomputing 58(60), 857–864 (2004)CrossRefGoogle Scholar
  5. 5.
    Di Paolo, E.A.: Spike-timing dependent plasticity for evolved robots. Adaptive Behavior 10(3), 243–263 (2002)CrossRefGoogle Scholar
  6. 6.
    Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. on Neural Networks 14(6), 1569–1572 (2003)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Izhikevich, E.M.: Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting. The MIT press, Cambridge (2007)Google Scholar
  8. 8.
    Murphy, P.M., Aha, D.W.: UCI repository of machine learning databases. Dept. Inf. Comput. Sci., Univ. California, Irvine (1994)Google Scholar
  9. 9.
    Vazquez, R.A., Sossa, H.: A new associative model with dynamical synapses. Neural Processing Letters 28(3), 189–207 (2008)CrossRefGoogle Scholar
  10. 10.
    Vazquez, R.A., Cachon, A.: Integrate and fire neurons and their application in pattern recognition. In: Proceedings of the 7th CCE, pp. 424–428 (2010)Google Scholar
  11. 11.
    Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: Proceedings of IEEE International Conference on Neural Networks, vol. IV, pp. 1942–1948 (1995)Google Scholar
  12. 12.
    Zhao, L., Yang, Y.: PSO-Based Single Multiplicative Neuron Model for Time Series Prediction. Expert Systems with Applications 36, 2805–2812 (2009)CrossRefGoogle Scholar
  13. 13.
    Yu, J., et al.: An Improved Particle Swarm Optimization for Evolving Feedforward Artificial Neural Networks. Neural Processing Letters 26, 217–231 (2007)CrossRefGoogle Scholar
  14. 14.
    Gudise, V.G., Venayagamoorthy, G.K.: Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks. In: Proceedings of the IEEE Swarm Intelligence Symposium, pp. 110–117 (2003)Google Scholar
  15. 15.
    Vázquez, R.A.: Pattern recognition using spiking neurons and firing rates. In: Kuri-Morales, A., Simari, G.R. (eds.) IBERAMIA 2010. LNCS, vol. 6433, pp. 423–432. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  16. 16.
    Hamed, H.N., Kasabov, N., Michlovský, Z., Shamsuddin, S.M.: String Pattern Recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization. In: Leung, C.S., Lee, M., Chan, J.H. (eds.) ICONIP 2009. LNCS, vol. 5864, pp. 611–619. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  17. 17.
    Kamoi, S., et al.: Pulse Pattern Training of Spiking Neural Networks Using Improved Genetic Algorithm. In: Proceedings of the IEEE CIRA, pp. 977 – 981 (2003)Google Scholar
  18. 18.
    Hong, S., et al.: A Cooperative Method for Supervised Learning in Spiking Neural Networks. In: 14th CSCWD, pp. 22–26 (2010)Google Scholar
  19. 19.
    Vazquez, R.A.: Izhikevich Neuron Model and its Application in Pattern Recognition. Australian Journal of Intelligent Information Processing Systems 11, 35–40 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Roberto A. Vázquez
    • 1
  • Beatriz A. Garro
    • 2
  1. 1.Intelligent Systems Group Faculty of EngineeringLa Salle UniversityCondesaMéxico
  2. 2.Center for Computing ResearchIPNVallejoMéxico

Personalised recommendations