10.9k citations
- Massachusetts Institute of TechnologyUS244 papers
- Harvard UniversityUS214 papers
- The Ohio State UniversityUS152 papers
- University of Wisconsin–MadisonUS147 papers
- Lawrence Berkeley National LaboratoryUS144 papers
- University of OxfordGB140 papers
- University of LiverpoolGB138 papers
- University of PisaIT138 papers
- Johns Hopkins UniversityUS135 papers
- Sapienza University of RomeIT133 papers
- Center for Astrophysics Harvard & SmithsonianUS131 papers
- University of MichiganUS131 papers
64 papers · 1 filter
Detecting Hate Speech in Social Media
Shervin Malmasi, Marcos Zampieri
In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by app…
Judicious Judgment Meets Unsettling Updating: Dilation, Sure Loss, and Simpson's Paradox
Ruobin Gong, Xiao-Li Meng
Statistical learning using imprecise probabilities is gaining more attention because it presents an alternative strategy for reducing irreplicable findings by freeing the user from…
Key Science Goals for the Next Generation Very Large Array (ngVLA): Report from the ngVLA Science Advisory Council
Alberto D. Bolatto, Shami Chatterjee, Caitlin M. Casey +20
This document describes some of the fundamental astrophysical problems that require observing capabilities at millimeter- and centimeter wavelengths well beyond those of existing,…
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
Andrew Slavin Ross, Finale Doshi-Velez
Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their…
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
Mike Wu, Michael C. Hughes, Sonali Parbhoo +3
The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step…
Practical Whole-System Provenance Capture
Thomas Pasquier, Xueyuan Han, Mark Goldstein +4
Data provenance describes how data came to be in its present form. It includes data sources and the transformations that have been applied to them. Data provenance has many uses, f…