Causality for Explanations and Other Applications

In this seminar, 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. Dr. Chockler explains the definitions informally using examples from formal verification. She also introduces the definition of responsibility, which quantifies the definition of causality, again using an example from formal methods (which historically was the first application of responsibility).

Also looking in more detail at the application of causality to explanations of AI decisions and discuss some examples. Finally, touching upon the concept of fairness and discrimination in causal models.