Heinz College Faculty Research Seminar

  • DAVID JENSEN
  • Professor
  • College of Information and Computer Sciences
  • University of Massachusetts
Seminars

Explainable Artificial Intelligence: Opportunities and Challenges for Public Policy

Advances in artificial intelligence are increasingly powering critical infrastructure across nearly all areas of human activity, including healthcare, transportation, security, finance, education, media, and government.  However, many of the most advanced and capable systems are largely opaque, having been developed by applying machine learning techniques to massive amounts of data.  This has spurred interest in explainable artificial intelligence, a class of techniques intended to automatically provide accurate explanations of the decisions produced by extremely complex AI systems.  In this talk, I will define explainable AI and discuss the goals of current research.  I will identify various technical approaches being taken by researchers working in the area, and I will provide examples of some of the most recent research results.  I will identify and discuss some common myths about explainable AI, and I will describe some very real and challenging public policy questions about the role of AI systems in critical infrastructure.  Finally, I will show how explainable AI could alleviate some of those policy concerns, and also how it may create the need for new roles and structures within public institutions.

 —

David Jensen is a Professor of Computer Science at the University of Massachusetts Amherst.  From 1991 to 1995, he served as an analyst with the Office of Technology Assessment, an agency of the U.S. Congress.  His current research focuses on methods to learn accurate causal models of large social, technological, and computational systems.  His most recent work focuses on applying causal inference methods to explaining the reasoning of AI systems.  He regularly serves on program committees for several conferences, including the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, the IEEE International Conference on Data Mining, the International Conference on Machine Learning, and the Conference on Uncertainty in Artificial Intelligence.  He has served on the Board of Directors of the ACM Special Interest Group on Knowledge Discovery and Data Mining (2005-2013), the Defense Science Study Group (2006-2007), and DARPA's Information Science and Technology Group (2007-2012).  In 2011, he received the Outstanding Teacher Award from the UMass College of Natural Sciences.  In 2017, one of his papers received the IEEE INFOCOM Test of Time Paper Award.

Lunch served.

 

For More Information, Please Contact: 
Keywords: