Publication Details

Title: Generalization and Parameter Estimation in Feedforward Nets: Some
Author: N. Morgan and H. Bourlard
Group: ICSI Technical Reports
Date: April 1989
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-89-17.pdf

Overview:
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.

Bibliographic Information:
ICSI Technical Report TR-89-017

Bibliographic Reference:
N. Morgan and H. Bourlard. Generalization and Parameter Estimation in Feedforward Nets: Some. ICSI Technical Report TR-89-017, April 1989