I will present the 'virtual democracy' framework for the design of ethical AI. In a nutshell, the framework consists of three steps: first, collect preferences from voters on example dilemmas; second, learn models of their preferences, which generalize to any (previously unseen) dilemma; and third, at runtime, predict the voters' preferences on the current dilemma, and aggregate these virtual 'votes' using a voting rule to reach a decision. I will focus on two instantiations of this approach: a proof-of concept system that decides ethical dilemmas potentially faced by autonomous vehicles, and a decision support tool designed to help a Pittsburgh-based nonprofit allocate food donations to recipient organizations. These projects bridge AI, social choice theory, statistics, and human-computer interaction; I will discuss challenges in all of these areas.
Ariel Procaccia is an Associate Professor in the Computer Science Department at Carnegie Mellon University. He works on a broad and dynamic set of problems related to AI, algorithms, economics, and society. His distinctions include a Guggenheim Fellowship (2018), the IJCAI Computers and Thought Award (2015), a Sloan Research Fellowship (2015), an NSF CAREER Award (2014), and the IFAAMAS Victor Lesser Distinguished Dissertation Award (2009). To make his research accessible to the public, he has founded the not-for-profit websites Spliddit.org and RoboVote.org, and has written op-eds for the Washington Post, Wired, and Bloomberg (where he is a regular contributor).