Delta rule

From AMS Glossary
Jump to: navigation, search


delta rule

Method of training a neural network using backpropagation.

The error in the output of the neural network (e.g., a prediction of minimum nighttime temperature) is a function of the values of the input parameters (cloud cover, 6
ams2001glos-Dex03
temperature, etc.) and the weights assigned to them. The weights are adjusted to minimize the error. Application of the delta rule results in the most rapid error reduction (learning rate). The learning rate can be adjusted as necessary to avoid being trapped in a local error minimum.

Personal tools
Namespaces
Variants