Skip to the main content

Finale Doshi-Velez

Finale Doshi-Velez is excited about methods to turn data into actionable knowledge.  Her core research in machine learning, computational statistics, and data science is inspired by---and often applied to---the objective of accelerating scientific progress and practical impact in healthcare and other domains.

Specifically, she is interested in questions such as: How can we design robust, principled models to combine complex data sets with other knowledge sources?  How can we design models that summarize and generate hypotheses from such data?  How can we characterize the uncertainty in large, heterogeneous data to provide better support for decisions?  Finale Doshi-Velez is interested in developing the probabilistic methods to address these questions.

Prior to joining SEAS, Finale Doshi-Velez was an NSF CI-TRaCS Postdoctoral Fellow at the Center for Biomedical Informatics at Harvard Medical School.  She was a Marshall Scholar at Trinity College, Cambridge from 2007-2009, and she was named one of IEEE's "AI Top 10 to Watch" in 2013.


Projects & Tools

AI: Transparency and Explainability

There are many ways to hold AI systems accountable. We focus on issues related to obtaining human-intelligible and human-actionable information. More


Publications

Monday, Nov 27, 2017

Accountability of AI Under the Law: The Role of Explanation

The paper reviews current societal, moral, and legal norms around explanations, and then focuses on the different contexts under which an explanation is currently required under… More


News

Washington Post
Tuesday, Mar 20, 2018

AI is more powerful than ever. How do we hold it accountable?

Trying to understand advanced AI is like trying to understand the inner workings of another person’s mind. More