Robustness of Artificial Metaplasticity Learning to Erroneous Input Distribution Assumptions

  • Marta de Pablos Álvaro
  • Diego Andina
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7930)

Abstract

Artificial Metaplasticity learning algorithm is inspired by the biological metaplasticity property of neurons and Shannon’s information theory. In this research, Artificial Metaplasticity on multilayer perceptron (AMMLP) is compared with regular Backpropagation by using input sets generated with different probability distributions: Gaussian, Exponential, Uniform and Rayleigh. Artificial Metaplasticity shows better results than regular Backpropagation for Gaussian and Uniform distribution while regular Backpropagation shows better results for Exponential and Rayleigh distributions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jedlicka, P.: Synaptic plasticity, metaplasticity and BCM theory 103(4), 137–143 (2002)Google Scholar
  2. 2.
    Malenka, R., Bear, M.: LTP and LTD: An Embarrassment of Riches. Neuron 44(1), 5–21 (2004), doi:10.1016/j.neuron.2004.09.012CrossRefGoogle Scholar
  3. 3.
    Abraham, W.C.: Activity-dependent regulation of synaptic plasticity (metaplasticity) in the hippocampus. In: Kato, N. (ed.) The Hippocampus: Functions and Clinical Relevance, pp. 15–26. Elsevier, Amsterdam (1996)Google Scholar
  4. 4.
    Abraham, W.C.: Metaplasticity: Key Element in Memory and Learning? News in Physiological Sciences 14(2), 85 (1999)Google Scholar
  5. 5.
    Abraham, W.C., Bear, M.F.: Metaplasticity: The plasticity of synaptic plasticity. Trends in Neurosciences 19, 126–130 (1996), doi:10.1016/S0166-2236(96)80018-XCrossRefGoogle Scholar
  6. 6.
    Kinto, E.A., Del Moral Hernandez, E., Marcano, A., Ropero Peláez, J.: A preliminary neural model for movement direction recognition based on biologically plausible plasticity rules. In: Mira, J., Álvarez, J.R. (eds.) IWINAC 2007. LNCS, vol. 4528, pp. 628–636. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Chiappalone, M., Vato, A., Berdondini, L., Koudelka, M., Martinoia, S.: Network Dynamics and Synchronous Activity in Cultured Cortical Neurons. Int. J. Neural Syst. 17(2), 87–103 (2007)CrossRefGoogle Scholar
  8. 8.
    Andina, D., Alvarez-Vellisco, A., Jevtic, A., Fombellida, J.: Artificial metaplasticity can improve artificial neural network learning. Intelligent Automation and Soft Computing, SI on Signal Processing and Soft Computing 15, 683–696 (2009) ISSN: 1079-8587Google Scholar
  9. 9.
    Marcano-Cedeño, A., Quintanilla-Domínguez, J., Andina, D.: Breast cancer classification applying artificial metaplasticity algorithm. Neurocomputing, doi:10.1016/j.neucom.2010.07.019Google Scholar
  10. 10.
    Marcano-Cedeño, A., Martín de la Bárcena, A., Jiménez-Trillo, J., Piñuela, J.A., Andina, D.: Artificial Metaplasticity Neural Network Applied to Credit Scoring. Int. J. Neural Syst. 21(4), 311–317 (2011), doi:10.1142/S0129065711002857CrossRefGoogle Scholar
  11. 11.
    Marcano-Cedeño, A., Quintanilla-Domínguez, J., Andina, D.: Wood Defects Classification Using Artificial Metaplasticity Neural Network. In: Proc. 35th Annual Conf. on of the IEEE Industrial Electronics Society, Porto, Portugal, pp. 3422–3427 (2009), doi:10.1109/IECON.2009.5415189Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Marta de Pablos Álvaro
    • 1
  • Diego Andina
    • 1
  1. 1.Group for Automation in Signals and CommunicationsTechnical University of MadridSpain

Personalised recommendations