A General Purpose Image Processing Chip: Orientation Detection

Abstract

The generalization ability of a neural network can sometimes be improved dramatically by regularization. To analyze the improve(cid:173) ment one needs more refined results than the asymptotic distri(cid:173) bution of the weight vector. Here we study the simple case of one-dimensional linear regression under quadratic regularization, i.e., ridge regression. We study the random design, misspecified case, where we derive expansions for the optimal regularization pa(cid:173) rameter and the ensuing improvement. It is possible to construct examples where it is best to use no regularization.

Cite

Text

Etienne-Cummings and Cai. "A General Purpose Image Processing Chip: Orientation Detection." Neural Information Processing Systems, 1997.

Markdown

[Etienne-Cummings and Cai. "A General Purpose Image Processing Chip: Orientation Detection." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/etiennecummings1997neurips-general/)

BibTeX

@inproceedings{etiennecummings1997neurips-general,
  title     = {{A General Purpose Image Processing Chip: Orientation Detection}},
  author    = {Etienne-Cummings, Ralph and Cai, Donghui},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {873-879},
  url       = {https://mlanthology.org/neurips/1997/etiennecummings1997neurips-general/}
}