Search Results for author: Mark Craven

Found 3 papers, 2 papers with code

Feature Importance Explanations for Temporal Black-Box Models

2 code implementations23 Feb 2021 Akshay Sood, Mark Craven

Models in the supervised learning framework may capture rich and complex representations over the features that are hard for humans to interpret.

Feature Importance

Understanding Learned Models by Identifying Important Features at the Right Resolution

1 code implementation18 Nov 2018 Kyubin Lee, Akshay Sood, Mark Craven

In many application domains, it is important to characterize how complex learned models make their decisions across the distribution of instances.

Two-sample testing

Multiple-Instance Active Learning

no code implementations NeurIPS 2007 Burr Settles, Mark Craven, Soumya Ray

In particular, we consider the case in which an MI learner is allowed to selectively query unlabeled instances in positive bags.

Active Learning text-classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.