Learning networks for process identification and associative action

  • Lisa Borland
  • Hermann Haken
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 686)


Using short-time correlation function measurements of an observed process as input, we show that it is possible to train a network to learn the non-linear stochastic dynamics underlying the process. Alternatively this can be formulated as a neural network with non-linear stochastic synapses, which can, after training, be used to associate actions.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    H.Haken, Information and Self-Organization, Springer-Verlag, Berlin-Heidelberg-New York 1988Google Scholar
  2. [2]
    L.Borland, H.Haken, Unbiased Determination of Forces Causing observed Processes, Z. Phys. B — Condensed Matter 81 (1992) 95Google Scholar
  3. [3]
    L.Borland, H. Haken, Unbiased Estimate of Forces from Measured Correlation Functions, including the Case of Strong Multiplicative Noise, Ann. Physik 1 (1992) 452Google Scholar
  4. [4]
    L.Borland, H. Haken, Learning the Dynamics of Two Dimensional Stochastic Markov Processes, to be published in Open Systems and Information DynamicsGoogle Scholar
  5. [5]
    E.T. Jaynes, Phs. Rev 106 (1957) 4,620Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Lisa Borland
    • 1
  • Hermann Haken
    • 1
  1. 1.Institute for Theoretical Physics and SynergeticsUniversity of StuttgartStuttgart 80

Personalised recommendations