Generalization and Parameter Estimation in Feedforward Nets: Some Experiments
Abstract
We have done an empirical study of the relation of the number of parameters (weights) in a feedforward net to generalization perfor(cid:173) mance. Two experiments are reported. In one, we use simulated data sets with well-controlled parameters, such as the signal-to-noise ratio of continuous-valued data. In the second, we train the network on vector-quantized mel cepstra from real speech samples. In each case, we use back-propagation to train the feedforward net to discriminate in a multiple class pattern classification problem. We report the results of these studies, and show the application of cross-validation techniques to prevent overfitting.
Cite
Text
Morgan and Bourlard. "Generalization and Parameter Estimation in Feedforward Nets: Some Experiments." Neural Information Processing Systems, 1989.Markdown
[Morgan and Bourlard. "Generalization and Parameter Estimation in Feedforward Nets: Some Experiments." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/morgan1989neurips-generalization/)BibTeX
@inproceedings{morgan1989neurips-generalization,
title = {{Generalization and Parameter Estimation in Feedforward Nets: Some Experiments}},
author = {Morgan, N. and Bourlard, H.},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {630-637},
url = {https://mlanthology.org/neurips/1989/morgan1989neurips-generalization/}
}