Principal Researcher in the New York City lab of Microsoft Research and an Adjunct Assistant Professor in the Department of Information Science at Cornell University. 

Title: Unavoidable Tensions in Explaining Algorithmic Decisions

Abstract: Recent developments in methods for explaining the decisions of machine learning models have been widely embraced for their ability to provide transparency and accountability without limiting model complexity or compelling model disclosure. Yet applying these methods is far from straightforward and they rarely prove a cure all. This talk identifies a number of unavoidable tensions that practitioners must navigate as they seek to employ these methods—and the deeply subjective judgments that must go into these considerations.

Assistant Professor, Computer Science, Stanford University

Title: Explainability in AI Measurement and Scaling

Abstract: Explainability is typically focused on individual AI models and particular prediction patterns. Yet, the advent of large-scale AI models highlights a new explainability frontier: explainability of AI measurements and benchmarks, especially with respect to predictability with scale. This talk will outline some of our emerging research in the search for the explainability of AI measurements with scale and discuss some mechanisms for addressing the explainability gap.

Professor in Financial Computing and Risk Modelling within he Artificial Intelligence Applications Institute, Informatics, University of Edinburgh

Head of RegTech, Data and Innovation at the Bank of England 

Professor in Computational Logic at the Department of Computing, Imperial College London and Royal Academy of Engineering / J.P. Morgan Research Chair in Argumentation-based Interactive Explainable AI