Advertisement

Lattice Neural Networks with Spike Trains

  • Gerhard X. Ritter
  • Gonzalo Urcid
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6077)

Abstract

Lattice based neural networks have proven their capability of resolving difficult non-linear problems and have been successfully employed to resolve real-world problems. In this paper we introduce a novel lattice neural net that generalizes previous dendritic models. The new model employs the biological notion of dendritic spines and spike trains. We show by example that it can accomplish tasks previous lattice neural networks were incapable of achieving.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ritter, G.X., Urcid, G.: Lattice Algebra Approach to Single-Neuron Computation. IEEE Trans. on Neural Networks 14(2), 282–295 (2003)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Holmes, W.R., Rall, W.: Electronic Models of Neuron Dendrites and Single Neuron Computation. In: McKenna, T., Davis, J., Zornetzer, F. (eds.) Single Neuron Computation, pp. 7–25. Academic Press, New York (1992)Google Scholar
  3. 3.
    Koch, C., Poggio, T.: Multiplying with Synapses. In: McKenna, T., Davis, J., Zornetzer, F. (eds.) Single Neuron Computation, pp. 315–345. Academic Press, New York (1992)Google Scholar
  4. 4.
    Koch, C.: Biophysics of Computation: Information Processing in Single Neurons. Oxford University Press, Oxford (1999)Google Scholar
  5. 5.
    Mel, B.W.: Why have Dendrites? A Computational Perspective. In: Dendrites, S.G., Spruston, N., Hausser, M.D. (eds.) pp. 271–228. Oxford University Press, Oxford (1999)Google Scholar
  6. 6.
    Yu, A.J., Giese, M.A., Poggio, T.A.: Biophysiologically Plausible Implementations of the Maximum Operation. Neural Computation 14(12), 2857–2881 (2002)zbMATHCrossRefGoogle Scholar
  7. 7.
    Lampl, I., Ferster, D., Poggio, T., Riesenhuber, M.: Intracellular Measurements of Spatial Integration and the Max Operation in Complex Cells of the Cat Primary Visual Cortex. Journal of Neurophysiology 92, 2704–2713 (2004)CrossRefGoogle Scholar
  8. 8.
    Barmpoutis, A., Ritter, G.X.: Orthonormal Basis Lattice Neural Networks. In: Kaburlasos, V.G., Ritter, G.X. (eds.) Computational Intelligence based on Lattice Theory. SCI, vol. 67, pp. 45–58. Springer, Berlin (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Gerhard X. Ritter
    • 1
  • Gonzalo Urcid
    • 2
  1. 1.CISE DepartmentUniversity of FloridaGainesvilleUSA
  2. 2.Optics DepartmentINAOETonantzintlaMexico

Personalised recommendations