Anat Elhalal
Safety Research · 2019
A researcher in the Science corpus: 2 papers; trusts 10 researchers and is trusted by 2 researchers here, as inferred from the citation graph.
Subfields
- Safety Research — 53 citations into it; #4,547 of 5,829 by trust here, #3,668 by citations
- Artificial Intelligence — 46 citations into it; #30,242 of 35,345 by trust here, #25,040 by citations
- Safety, Robustness & Interpretability — 24 citations into it
- AI Ethics, Fairness & Society — 20 citations into it
- Cognitive Neuroscience — 15 citations into it; #8,555 of 10,852 by trust here, #7,860 by citations
- Health Informatics — 14 citations into it
- Information Systems — 9 citations into it
- Information Systems and Management — 5 citations into it
Whom Anat Elhalal trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Who trusts Anat Elhalal overall
Papers from Anat Elhalal's perspective
Ordered by how strongly the researchers Anat Elhalal trusts endorse each paper. Same corpus, a different order for every researcher.
- The mythos of model interpretability
- How the machine ‘thinks’: Understanding opacity in machine learning algorithms
- A Unified Approach to Interpreting Model Predictions
- European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation"
- Algorithmic Accountability and Public Reason
- The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards
- Disparate Impact in Big Data Policing
- Artificial Intelligence: the global landscape of ethics guidelines
- A Unified Framework of Five Principles for AI in Society
- Data ethics