Goto

Collaborating Authors

 point classification



questions, but not all, due to space limitations; the minor questions will all be dealt with in the revision

Neural Information Processing Systems

We thank all the reviewers for their insightful comments and encouraging remarks. Our innovation is not intended to be the development of new ML techniques, but lends itself to the application setting. Hence, the value of our contribution is not as a "final say", but in setting up a strong baseline to entice "Only evaluated on one dataset, limiting applications (R3)." Sorry, this is not quite true. Paper should be more self-contained (R1 & R2).