RBF networks for density estimation

A non-parametric probability density function (pdf) estimation technique is presented. The estimation consists in approximating the unknown pdf by a network of Gaussian Radial Basis Functions (GRBFs). Complexity analysis is introduced in order to select the optimal number of GRBFs. Results obtained on real data show the potentiality of this technique.

[1]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[2]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[3]  P Pudil,et al.  Simultaneous learning of decision rules and important attributes for classification problems in image analysis , 1994, Image Vis. Comput..

[4]  Hervé Bourlard,et al.  Probability estimation by feed-forward networks in continuous speech recognition , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[5]  J. Kittler,et al.  Minimum complexity estimator for RBF networks architecture selection , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[6]  Andrew R. Barron,et al.  Minimum complexity density estimation , 1991, IEEE Trans. Inf. Theory.