Generalization and Parameter Estimation in Feedforward Nets: Some

TitleGeneralization and Parameter Estimation in Feedforward Nets: Some
Publication TypeTechnical Report
Year of Publication1989
AuthorsMorgan, N., & Bourlard H.
Other Numbers516
Abstract

We have begun an empirical study of the relation of the number of parameters (weights) in a feedforward net to generalization performance. 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.

URLhttp://www.icsi.berkeley.edu/pubs/techreports/tr-89-17.pdf
Bibliographic Notes

ICSI Technical Report TR-89-017

Abbreviated Authors

N. Morgan and H. Bourlard

ICSI Research Group

Speech

ICSI Publication Type

Technical Report