How (Not) to Explain Blackbox AI Systems

Abstract: Explainability in machine learning and AI is emerging as a leading area of academic research and a topic of significant legal and regulatory concern. Indeed, a near-consensus is emerging in favour of explainable AI/ML among lawmakers, academics, and civil society groups. In this project, we challenge this prevailing trend. We argue that explaining AI/ML predictions is at best unnecessary or misleading and at worst socially harmful.  

About the Speaker: 

Dr. Boris Babic is HKU100 Associate Professor at the University of Hong Kong, hosted jointly by the Institute of Data Science, the Department of Philosophy, and (by courtesy) the Faculty of Law. His primary research interests are in legal and ethical issues surrounding the development of artificial intelligence. Before coming to HKU, he was tenure track assistant professor at the University of Toronto and at INSEAD in France and Singapore. He obtained his JD from Harvard Law School, his MS and PhD from the University of Michigan, and he completed a postdoc at the California Institute of Technology (Caltech).