Abstract
The commonly used technique of generating empirical univariate cumulative distribution functions is extended to bivariate cases. It is implemented by using the monotonic back-propagation leastmean square neural network. An algorithm to generate empirical bivariate cumulative distribution functions using the neural network model is defined. Examples of generating simulated data using the suggested technique are demonstrated.
Similar content being viewed by others
References
T. J. Schriber.An introduction to simulation using GPSS/H, John Wiley & Sons, New York, 1991.
D. Rumelhart, J. McClelland and the PDP Research Group.Parallel distributed processing: explorations in the microstructure of cognition, Volume 1: Foundations, The MIT Press, Cambridge, MA, 1986.
G. Cybenko. Approximation by superpositions of a sigmoidal function,Mathematics of Control, Signals and Systems, vol.2, pp. 303–314, 1989.
T. Kawabata. Generalization effects ofk-Neighbour interpolation training,Neural Computation, vol. 3, pp. 409–417, 1991.
N. P. Archer, S. Wang. Fuzzy set representation of neural network classification boundaries,IEEE Transactions on Systems, Man, And Cybernetics, vol. 21, pp. 735–742, 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wang, S. A neural network technique of generating empirical bivariate distribution functions. Neural Process Lett 2, 14–18 (1995). https://doi.org/10.1007/BF02332160
Issue Date:
DOI: https://doi.org/10.1007/BF02332160