Abstract

The Cambridge ELLIS Unit has started a Seminar Series that will include talks by leading researchers in the area of machine learning and AI. Our next speaker of the year will be Dr. Hana Chockler. Details of her talk can be found below.

Title: “Actual Causality, Explanations, and Fairness”

Abstract: In this talk, I will (briefly) introduce the theory of actual causality as defined by Halpern and Pearl. This theory turns out to be extremely useful in various areas of computer science due to a good match between the results it produces and our intuition. I will also introduce the definition of responsibility, which quantifies the definition of causality. We will then look in more detail at the applications of actual causality to the behaviour of black-box AI applications. Specifically, we will discuss two applications: explanations of (black-box) image classifiers and fairness and discrimination in black-box models.  The talk is based on a number of papers, and, while not strictly limited to my own research, the topics are quite broad and have been a subject of very active research, so I will be mostly talking about my work with different co-authors. The talk is reasonably self-contained. Bio: Dr Hana Chockler is a Principal Scientist at a startup company causaLens since 2020. causaLen’s mission is to apply causal reasoning to a wide array of domains. Dr Chockler also holds a post of Reader in Formal Methods in the Department of Informatics, King’s College London. Prior to joining KCL in 2013, Hana worked at IBM Research in the formal verification and software engineering departments. Dr Chockler’s research interests span a wide variety of topics, including formal verification and synthesis of hardware and software, and, most recently, causal reasoning applied to AI. https://eng-cam.zoom.us/j/83630301100?pwd=K1d6VnJwdWFKZ2JiODlYakFycDBlQT09