Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Across the world's coronavirus disease 2019 (COVID-19) hot spots, the need to streamline
patient diagnosis and management has become more pressing than ever. As one of the …

Machine learning models for medical image analysis often suffer from poor performance on
important subsets of a population that are not identified during training or testing. For …

We investigate whether post-hoc model explanations are effective for diagnosing model
errors--model debugging. In response to the challenge of explaining a model's prediction, a …

Machine learning models that achieve high overall accuracy often make systematic errors
on important subsets (or slices) of data. Identifying underperforming slices is particularly …

We investigate whether three types of post hoc model explanations–feature attribution,
concept activation, and training point ranking–are effective for detecting a model's reliance …

Interpretability in machine learning models is important in high-stakes decisions such as
whether to order a biopsy based on a mammographic exam. Mammography poses …

In machine learning, a question of great interest is understanding what examples are
challenging for a model to classify. Identifying atypical examples ensures the safe …

Over the past few years, we have seen fundamental breakthroughs in core problems in
machine learning, largely driven by advances in deep neural networks. At the same time, the …

Data provenance, a record that describes the origins and processing of data, offers new
promises in the increasingly important role of artificial intelligence (AI)-based systems in …