Kernel Regression and Backpropagation Training with Noise
Abstract
One method proposed for improving the generalization capability of a feed(cid:173) forward network trained with the backpropagation algorithm is to use artificial training vectors which are obtained by adding noise to the orig(cid:173) inal training vectors. We discuss the connection of such backpropagation training with noise to kernel density and kernel regression estimation. We compare by simulated examples (1) backpropagation, (2) backpropagation with noise, and (3) kernel regression in mapping estimation and pattern classification contexts.
Cite
Text
Koistinen and Holmström. "Kernel Regression and Backpropagation Training with Noise." Neural Information Processing Systems, 1991.Markdown
[Koistinen and Holmström. "Kernel Regression and Backpropagation Training with Noise." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/koistinen1991neurips-kernel/)BibTeX
@inproceedings{koistinen1991neurips-kernel,
title = {{Kernel Regression and Backpropagation Training with Noise}},
author = {Koistinen, Petri and Holmström, Lasse},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {1033-1039},
url = {https://mlanthology.org/neurips/1991/koistinen1991neurips-kernel/}
}