In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization algorithm. Wederive the generalization bounds of the proposedapproach. T…
We thank the organizers for systematically setting up this task, and for the very useful resources. We also thank the larger language processing group at IIIT Hyderabad for the encouragement, support and insights.
There aren't more papers