A New Learning Algorithm for Adaptive Spiking Neural Networks

  • J. Wang
  • A. Belatreche
  • L. P. Maguire
  • T. M. McGinnity
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7062)

Abstract

This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a ’virtual’ supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.

Keywords

spiking neurons supervised learning spike response model online learning offline learning adaptive structure classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Haykin, S.: Neural Networks: A Comprehensive Foundation. Macmillan College Publishing, New York (1999)MATHGoogle Scholar
  2. 2.
    Bohte, S.M., Kok, J.N., Poutre, H.L.: Error-backprogation in Temporally Encoded Networks of spiking neurons. In: Neurocomputing 48, 17–37 (2002)Google Scholar
  3. 3.
    Belatreche, A., Maguire, L.P., McGinnity, M., Wu, Q.: A Method for Supervised Training of Spiking Neural Networks. In: Proceedings of IEEE Cybernetics Intelligence - Challenges and Advances (CICA), Reading, UK, pp. 39–44 (2003)Google Scholar
  4. 4.
    Legenstein, R., Naeger, C., Maass, W.: What can a Neuron Learn with Spike-Timing-Dependent Plasticity? Neural Computation 17, 2337–2382 (2005)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Ponulak, F., Kasinski, A.: A novel approach towards movement control with Spiking Neural Networks. In: 3rd International Symposium on Adaptive Motion in Animals and MachinesIlmenau (2005)Google Scholar
  6. 6.
    Glackin, C., McDaid, L., Maguire, L., Sayers, H.: Implementing Fuzzy Reasoning on a Spiking Neural Network. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part II. LNCS, vol. 5164, pp. 258–267. Springer, Heidelberg (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • J. Wang
    • 1
  • A. Belatreche
    • 1
  • L. P. Maguire
    • 1
  • T. M. McGinnity
    • 1
  1. 1.Intelligent Systems Research Centre (ISRC) Faculty of Computing and EngineeringUniversity of UlsterDerryUnited Kingdom

Personalised recommendations