Opened 3 years ago

Last modified 8 months ago

#2812 assigned feature request

Use ConstrainedValueParameters in GaussianProcessRegression

Reported by: mkommend Owned by: fholzing
Priority: medium Milestone: HeuristicLab 3.3.17
Component: Algorithms.DataAnalysis Version:
Keywords: Cc:

Description

Currently the covariance and mean functions are set into ValueParameters. Therefore, the create experiment dialog cannot handle these two important algorithm properties and modelling with GPR is more cumbersome than it needs to be.

Change History (6)

comment:1 Changed 3 years ago by abeham

  • Version 3.3.14 deleted

comment:2 Changed 3 years ago by mkommend

  • Owner set to fholzing
  • Status changed from new to assigned

comment:3 Changed 3 years ago by gkronber

I highly doubt that this will be easy to solve. The issue only has low priority in my point of view.

comment:4 Changed 18 months ago by fholzing

  • Milestone changed from HeuristicLab 3.3.16 to HeuristicLab 3.3.17

comment:5 Changed 8 months ago by fholzing

r17427: Changed type of MeanFunctionParameter and CovarianceFunctionParameter from IValueParameter to IConstrainedValueParameter (+ initialization)

comment:6 Changed 8 months ago by fholzing

r17428: Adapted UnitTest (Instance-Comparison failed)

Note: See TracTickets for help on using tickets.