Sara Hooker
Coherent (United States)(US)
Publications by Year
Research Areas
Natural Language Processing Techniques, Topic Modeling, Explainable Artificial Intelligence (XAI), Adversarial Robustness in Machine Learning, Machine Learning and Data Classification
Most-Cited Works
- → The State of Sparsity in Deep Neural Networks(2019)439 cited
- → The (Un)reliability of Saliency Methods(2019)432 cited
- → A Benchmark for Interpretability Methods in Deep Neural Networks(2018)379 cited
- → Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims(2020)212 cited
- → Moving beyond “algorithmic bias is a data problem”(2021)160 cited
- → What Do Compressed Deep Neural Networks Forget?(2019)85 cited
- → Efficient Methods for Natural Language Processing: A Survey(2023)81 cited
- → Frontier AI Regulation: Managing Emerging Risks to Public Safety(2023)71 cited