Neural Networks for Density Estimation

Abstract

We introduce two new techniques for density estimation. Our ap(cid:173) proach poses the problem as a supervised learning task which can be performed using Neural Networks. We introduce a stochas(cid:173) tic method for learning the cumulative distribution and an analo(cid:173) gous deterministic technique. We demonstrate convergence of our methods both theoretically and experimentally, and provide com(cid:173) parisons with the Parzen estimate. Our theoretical results demon(cid:173) strate better convergence properties than the Parzen estimate.

Cite

Text

Magdon-Ismail and Atiya. "Neural Networks for Density Estimation." Neural Information Processing Systems, 1998.

Markdown

[Magdon-Ismail and Atiya. "Neural Networks for Density Estimation." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/magdonismail1998neurips-neural/)

BibTeX

@inproceedings{magdonismail1998neurips-neural,
  title     = {{Neural Networks for Density Estimation}},
  author    = {Magdon-Ismail, Malik and Atiya, Amir F.},
  booktitle = {Neural Information Processing Systems},
  year      = {1998},
  pages     = {522-528},
  url       = {https://mlanthology.org/neurips/1998/magdonismail1998neurips-neural/}
}