Loading...
Loading...

Go to the content (press return)

Learning with feed-forward neural networks: Three schemes to deal with the bias/variance trade-off

Author
Romero, E.
Type of activity
Theses
Other related units
Department of Computer Science
Defense's date
2004-11-30
Repository
http://hdl.handle.net/2117/93955 Open in new window
URL
http://hdl.handle.net/2117/93955 Open in new window
Abstract
In terms of the Bias/Variance decomposition, very flexible (i.e., complex) Supervised Machine Learning systems may lead to unbiased estimators but with high variance. A rigid model, in contrast, may lead to small variance but high bias. There is a trade-off between the bias and variance contributions to the error, where the optimal performance is achieved.

In this work we present three schemes related to the control of the Bias/Variance decomposition for Feed-forward Neural Networks (FN...
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
SOCO - Soft Computing
Citation
Romero Merino, E. "Learning with Feed-forward Neural Networks: Three Schemes to Deal with the Bias/Variance Trade-off". Tesi doctoral, UPC, Departament de Llenguatges i Sistemes Informàtics, 2004.

Participants

Attachments