The Possibility of Explanation
Artificial intelligences are simultaneously becoming more complex and more ubiquitous. Used in fields such as medicine, finance, and insurance and many others, we need ways to hold them accountable. Designing AIs to provide explanation for their decisions is one powerful tool to prevent errors and still reap the benefits.
Finale Doshi-Velez is an Assistant Professor of Computer Science at the Harvard Paulson School of Engineering and Applied Sciences. Her interests lie at the intersection of machine learning and healthcare. She completed her PhD at MIT, her postdoc at Harvard Medical School, and is a Marshall Scholar.