This package provides an implementation Schapire and Singer's AdaBoost.MH for multi-label classification. As a main feature, the package provides decision-tree weak learning, a generalization of decision stumps that allows AdaBoost to learn conjunctions of original features. The implementation is specially suited for Natural Language classification taks, as it relies on sparse representations of examples and high-dimensional binary-feature spaces.
- 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.