Opened 12 years ago

Closed 12 years ago

Last modified 10 years ago

#717 closed defect (done)

SVM regression engine takes a very long time to finish

Reported by: gkronber Owned by: gkronber
Priority: low Milestone: HeuristicLab 3.3.0
Component: ZZZ OBSOLETE: SupportVectorMachines Version: 3.2
Keywords: Cc:

Description

Maybe a better approach would be to use a smaller training set and cross-validation for parameter tuning and then train a final model with the best parameters.

Change History (6)

comment:1 Changed 12 years ago by gkronber

  • Status changed from new to assigned

comment:2 Changed 12 years ago by gkronber

Changed variable impact calculation operators to use the actual training sub-set instead of the full training set with r2242.

comment:3 Changed 12 years ago by gkronber

Reduced the actual training set for SVM from 5000 to 1000 samples to improve the speed of the parameter search with r2251.

comment:4 Changed 12 years ago by gkronber

  • Resolution set to fixed
  • Status changed from assigned to closed

comment:5 Changed 10 years ago by swagner

  • Milestone changed from Iteration 4 to Current

Milestone Iteration 4 deleted

comment:11 Changed 10 years ago by swagner

  • Milestone changed from Current to HeuristicLab 3.3.0

Milestone Current deleted

Note: See TracTickets for help on using tickets.