The Rectified Gaussian Distribution

Abstract

A simple but powerful modification of the standard Gaussian dis(cid:173) tribution is studied. The variables of the rectified Gaussian are constrained to be nonnegative, enabling the use of nonconvex en(cid:173) ergy functions. Two multimodal examples, the competitive and cooperative distributions, illustrate the representational power of the rectified Gaussian. Since the cooperative distribution can rep(cid:173) resent the translations of a pattern, it demonstrates the potential of the rectified Gaussian for modeling pattern manifolds.

Cite

Text

Socci et al. "The Rectified Gaussian Distribution." Neural Information Processing Systems, 1997.

Markdown

[Socci et al. "The Rectified Gaussian Distribution." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/socci1997neurips-rectified/)

BibTeX

@inproceedings{socci1997neurips-rectified,
  title     = {{The Rectified Gaussian Distribution}},
  author    = {Socci, Nicholas D. and Lee, Daniel D. and Seung, H. Sebastian},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {350-356},
  url       = {https://mlanthology.org/neurips/1997/socci1997neurips-rectified/}
}