Empowering End-Users through AI Transparency and Interpretability

In this segment of the Media Lab Perspective Series, Professor Hiroshi Ishii will welcome Fernanda Viégas, a Principal Scientist at Google, in a discussion titled "Empowering End-users Through AI Transparency and Interpretability."

Machine learning is playing an increasingly influential role in the world due to dramatic technical leaps in recent years. Yet, it can often be challenging for these systems to meet end-user needs in practice. For instance, user trust is one of the hardest challenges in the adoption of AI-systems in high-stakes domains such as healthcare. This presentation will cover how AI interpretability and transparency techniques aimed at end-users, instead of ML experts, can help put people in control of ML systems, empowering them to more easily dialogue with these systems and supporting users in calibrating the correct level of trust. 

Speaker Bio

Fernanda Viégas is a Principal Scientist at Google, where she co-leads the PAIR  (People+AI Research) initiative, part of Google Brain. She is also the incoming Gordon McKay Professor of Computer Science at Harvard and Alumnae Professor at the Radcliffe Institute for Advanced Study in 2022, where she will be affiliated with Harvard Business School. Her work in machine learning, with long-time colleague Martin Wattenberg, focuses on improving human-AI interaction with a broader agenda of democratizing AI technology. She is well known for her contributions to social and collaborative visualization, and the systems she and her team have created are used daily by millions of people. Her visualization-based artwork with Wattenberg has been exhibited worldwide, and is part of the permanent collection of the Museum of Modern Art in New York. Fernanda holds a Ph.D. from the MIT Media Lab. Learn more: http://www.fernandaviegas.com/about.