A Universal Approximator Network for Learning Conditional Probability Densities

  • D. Husmeier
  • D. Allen
  • J. G. Taylor
Part of the Operations Research/Computer Science Interfaces Series book series (ORCS, volume 8)


A general approach is developed to learn the conditional probability density for a noisy time series. A universal architecture is proposed, which avoids difficulties with the singular low-noise limit. A suitable error function is presented enabling the probability density to be learnt. The method is compared with other recently developed approaches, and its effectiveness demonstrated on a time series generated from a non-trivial stochastic dynamical system.


Hide Layer Output Weight Conditional Probability Distribution Kernel Width Conditional Probability Density 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Allen DW and Taylor JG, Learning Time Series by Neural Networks, Proc ICANN (1994), ed Marinaro M and Morasso P, Springer, pp529–532.Google Scholar
  2. [2]
    Neuneier R, Hergert F, Finnoff W and Ormoneit D, Estimation of Conditional Densities: A Comparison of Neural Network Approaches, Proc ICANN (1994), ed Marinaro M and Morasso P, Springer, pp689–692.Google Scholar
  3. [3]
    Papoulis, A., Probability, Random Variables and Stochastic Processes, McGraw-Hill (1984).Google Scholar
  4. [4]
    Srivastava AN and Weigend AS, Computing the Probability Density in Connectionist Regression, Proc ICANN (1994), ed Marinaro M and Morasso P, Springer, pp685–688.Google Scholar
  5. [5]
    Weigend AS and Nix DA, Predictions with Confidence Intervals (Local Error Bars), Proc ICONIP (1994), ed Kim M-W and Lee S-Y, Korea Advanced Institute of Technology, pp847–852.Google Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • D. Husmeier
    • 1
  • D. Allen
    • 1
  • J. G. Taylor
    • 1
  1. 1.Centre for Neural Networks, Department of MathematicsKing’s College LondonUK

Personalised recommendations