ML Anthology

Complexity Analysis of RBF Networks for Pattern Recognition

Lucia Sardo, Josef Kittler
CVPR 1996 pp. 574-579
doi:10.1109/CVPR.1996.517130 /cvpr/1996/sardo1996cvpr-complexity/

Abstract

The problem of non-parametric probability density function (PDF) estimation using Radial Basis Function (RBF) Neural Networks is addressed here. We investigate two criteria, based on a modified Kullback-Leibler distance, that lead to an appropriate choice of the network architecture complexity. In the first criterion the modification consists in the addition of a term that penalizes complex architectures (MPL criterion). The second strategy, involves the regularization of the network through the imposition of lower bounds on the standard deviation derived from conditions of existence of rejection tests (LBSD criterion). Experimental results indicate that the MPL criterion outperforms the LBSD method.

CVPR Semantic Scholar

Cite

Text

Sardo and Kittler. "Complexity Analysis of RBF Networks for Pattern Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517130

Markdown

[Sardo and Kittler. "Complexity Analysis of RBF Networks for Pattern Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/sardo1996cvpr-complexity/) doi:10.1109/CVPR.1996.517130

BibTeX

@inproceedings{sardo1996cvpr-complexity,
  title     = {{Complexity Analysis of RBF Networks for Pattern Recognition}},
  author    = {Sardo, Lucia and Kittler, Josef},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {574-579},
  doi       = {10.1109/CVPR.1996.517130},
  url       = {https://mlanthology.org/cvpr/1996/sardo1996cvpr-complexity/}
}