causaLens logocausaLens logo alternate

Physical

Actual Causality, Explanations, and Fairness

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.

Dr. Hana Chockler introduces 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. She introduces the definition of responsibility, which quantifies the definition of causality. Dr. Chockler also speaks in detail about the applications of actual causality to the behavior of black-box AI applications. Specifically, she discusses two applications: explanations of (black-box) image classifiers and fairness and discrimination in black-box models.