Training Neural Networks with Deficient Data
Abstract
We analyze how data with uncertain or missing input features can be incorporated into the training of a neural network. The gen(cid:173) eral solution requires a weighted integration over the unknown or uncertain input although computationally cheaper closed-form so(cid:173) lutions can be found for certain Gaussian Basis Function (GBF) networks. We also discuss cases in which heuristical solutions such as substituting the mean of an unknown input can be harmful.
Cite
Text
Tresp et al. "Training Neural Networks with Deficient Data." Neural Information Processing Systems, 1993.Markdown
[Tresp et al. "Training Neural Networks with Deficient Data." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/tresp1993neurips-training/)BibTeX
@inproceedings{tresp1993neurips-training,
title = {{Training Neural Networks with Deficient Data}},
author = {Tresp, Volker and Ahmad, Subutai and Neuneier, Ralph},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {128-135},
url = {https://mlanthology.org/neurips/1993/tresp1993neurips-training/}
}