Speaker:Prof. Avi Rosenfeld
Title: Defining and Evaluating Explainable Artificial Intelligence (XAI)
As the field of Artificial Intelligence matures and becomes ubiquitous, there is a growing emergence of systems where people and agents work together. These systems, often called Human-Agent Systems or Human-Agent Cooperatives, have moved from theory to reality in the many forms, including digital personal assistants, recommendation systems, training and tutoring systems, service robots, chat bots, planning systems and self-driving cars. As such, this issue is quickly becoming a hot topic of great interest.
My talk will focus on one aspect of this human-agent interaction — the level of explainability that agents using machine learning must have regarding the decisions they make. I will provide a survey of this issue in Human-Agent Systems, first formally define explainability as well as the concepts of interpretability, transparency, explicitness, and faithfulness. Through using these definitions, I will focus on several open issues related to this problem through a taxonomy regarding the Why, Who, What, When, and How about explainability. I will then focus on several new projects I am currently studying relating to how explainability can be evaluated in several real-world problems.
Avi Rosenfeld (Ph.D. Computer Science, Bar Ilan University, 2007) is an Associate Professor of Computer Science at the Jerusalem College of Technology (JCT). His research generally focuses on data science and artificial intelligence research, and specifically how to reason through machine learning and data mining algorithms to build more accurate and explainable models. His research has created theoretical and practical applications for problems such as robotic coordination, peer to peer full-text search, human-computer interactions, data filtering, scheduling and constraint satisfaction and optimization, communication protocols, scalability issues and medical data analysis. He has published over 80 papers in leading conferences and journals.