Opened 12 years ago
Closed 4 years ago
#1935 closed feature request (rejected)
Support available covariance functions also as kernels in the SVM
| Reported by: | gkronber | Owned by: | gkronber |
|---|---|---|---|
| Priority: | lowest | Milestone: | |
| Component: | Algorithms.DataAnalysis | Version: | |
| Keywords: | Cc: |
Description
In ticket #1902 a number of covariance functions for Gaussian processes have been implemented. It should be possible to select these covariance functions also when configuring the kernel function for SVMs
Change History (2)
comment:1 Changed 7 years ago by gkronber
- Priority changed from medium to lowest
comment:2 Changed 4 years ago by gkronber
- Milestone HeuristicLab 3.3.x Backlog deleted
- Resolution set to rejected
- Status changed from new to closed
- Version 3.3.7 deleted
Note: See
TracTickets for help on using
tickets.
Related to #3074. We could support this with the native version by calculating the Gram matrix directly.