Automated parameter tuning
Previous  Top  Next

The PNC2 Cluster Algorithm contains several free parameters, that allow an adjustment of the algorithm's behavior to the actual learn data sample. However, one needs some experience to optimally chose the parameter values. Thus an automated parameter tuning component has been integrated into the PNC2 Rule Induction System. This chapter explains how it works.
 
·How to estimate the prediction accuracy  
Explains how the prediction accuracy is estimated using cross-validation or a similar approach  
 
·General settings  
Set the estimation method for the prediction method etc.  
 
·Define parameter sets  
How to define the standard parameter sets that are tested during the parameter tuning  
 
·Start the tuning process  
How to start or repeat the tuning process  
 
·How to select an optimal parameter set  
 
Note: You may skip the parameter tuning by just checking the check box Skip Tuning. This will immediately enable the group box Parameters and initialize the different values with suitable defaults.