Efficient implementation of penalized multiple logistic regression (aka multi-class) with Mercer kernels, aka MAP approximation to the multi-class Gaussian process model. This includes hyperparameter learning using an approximation to the cross-validation log likelihood (you need an optimizer to use this part).
This is MATLAB(R) plus MEX files code. If you want to seriously run this on big data, you should look at the LHOTSE klr project, where the same (and much more) is done stable and much faster.
I am happy about bug reports, but otherwise will not extend this anymore.
- Changes to previous version:
Initial Announcement on mloss.org.
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.