We present a method for determining the globally optimal on-line learning rule for a soft committee machine under a statistical mechanics framework. This rule maximizes the total reduction in generalization error over the whole learning process. A simple example demonstrates that the locally optimal rule, which maximizes the rate of decrease in generalization error, may perform poorly in comparison.
Bibliographical noteCopyright of the Institute of Physics.
- globally optimal on-line learning
- soft committee machine
- locally optimal rule