Advertisement

Deterministic Modelling of Randomness with Recurrent Artificial Neural Networks

  • Norman U. Baier
  • Oscar De Feo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)

Abstract

It is shown that deterministic (chaotic) systems can be used to implicitly model the randomness of stochastic data, a question arising when addressing information processing in the brain according to the paradigm proposed by the EC APEREST project. More precisely, for a particular class of recurrent artificial neural networks, the identification procedure of stochastic signals leads to deterministic (chaotic) models which mimic the statistical/spectral properties of the original data.

Keywords

Chaotic System Internal Node Chaos Synchronisation Chaotic Signal Chaotic Time Series 
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.
    De Feo, O., Hasler, M.: Modelling diversity by chaos and classification by synchronization. In: Pikovsky, A., Maistrenko, Y. (eds.) Synchronization: Theory and Application, pp. 25–40. Kluwer Academic Publishers, Dordrecht (2003)Google Scholar
  2. 2.
    De Feo, O.: Qualitative resonance of Shil’nikov-like strange attractors, part I: Experimental evidence. Int. J. Bifurcat. & Chaos 14, 873–891 (2004)zbMATHCrossRefGoogle Scholar
  3. 3.
    De Feo, O.: Qualitative resonance of Shil’nikov-like strange attractors, part II: Mathematical analysis. Int. J. Bifurcat. & Chaos 14, 893–912 (2004)zbMATHCrossRefGoogle Scholar
  4. 4.
    De Feo, O.: Self-emergence of chaos in the identification of irregular periodic behaviour. Chaos 13, 1205–1215 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Comput. 14, 2351–2560 (2002)CrossRefGoogle Scholar
  6. 6.
    Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304, 78–80 (2004)CrossRefGoogle Scholar
  7. 7.
    Jaeger, H.: The echo state approach to analysing and training recurrent neural networks. Technical Report 148, Fraunhofer Institute for Autonomous Intelligent Systems (2001)Google Scholar
  8. 8.
    Baier, N.: Approximately Periodic Time Series and Nonlinear Structures. PhD thesis, Ecole Polytechnique Fédérale de Lausanne (2005)Google Scholar
  9. 9.
    Maggio, G.M., De Feo, O., Kennedy, M.P.: Nonlinear analysis of the Colpitts oscillator and applications to design. IEEE T. Circuits-I 46, 1118–1130 (1999)zbMATHCrossRefGoogle Scholar
  10. 10.
    Schreiber, T., Schmitz, A.: Surrogate time series. Physica D 142, 197–385 (2000)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Candaten, M., Rinaldi, S.: Peak-to-Peak dynamics: A critical survey. International Journal of Bifurcation and Chaos 10, 1805–1819 (2000)zbMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Norman U. Baier
    • 1
  • Oscar De Feo
    • 1
  1. 1.Ecole Polytechnique Fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations