This package is a set of Matlab scripts that implements the algorithms described in the submitted paper: "Lp-Lq Sparse Linear and Sparse Multiple Kernel MultiTask Learning". This code is provided for a sake of result reproducibility.
The code needs the SVM-KM toolbox. some files of this toolbox have been included in a sub-directory (which needs to be in the Matlab path)
Some entry files are : Exsparsemtl.m, Exsparsemtlcomp.m For reproducing the toy data results, one can run the script Toylauncher.m or the CompareGDEMsparsemtl.m. The first script takes few days of CPU while the second finishes in few hours.
The BCI entry file is BCIcomparemtl.m which allows to reproduce the paper results. Since they are quite large the BCI data are not provided here (drop me a mail if you need them)
For the protein problem, launch exbioinfopq.m
- Changes to previous version:
Initial Announcement on mloss.org.
- BibTeX Entry: Download
- Corresponding Paper BibTeX Entry: Download
- URL: Project Homepage
- Supported Operating Systems: Platform Independent
- Data Formats: Matlab
- Tags: Support Vector Machine, Matlab, Mkl, Bci, Classification, Kernel Methods, Feature Selection, Convex Optimization, Dimensionality Reduction, Machine Learning, Feature Weighting, Group Lasso, Sparse Learning, Quadratic Programming, Multiple Kernel Learning, Kernel Learning, Discriminant Analysis
- Archive: download here
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.