Anchors as Explanations

We welcome back [Marco Tulio Ribeiro](https://homes.cs.washington.edu/~marcotcr/) to discuss research he has done since our original discussion on [LIME](https://dataskeptic.com/blog/episodes/2016/trusting-machine-learning-models-with-lime).

In particular, we ask the question [Are Red Roses Red?](https://homes.cs.washington.edu/~marcotcr/acl19_implication.pdf) and discuss how [Anchors](https://homes.cs.washington.edu/~marcotcr/aaai18.pdf) provide high precision model-agnostic explanations.

Please take our [listener survey](https://docs.google.com/forms/d/e/1FAIpQLSc7SbmG04zJFxrDsMH0uIm1geqKwDSJ6P3gq3oGl_9T251Pww/viewform).

Guest

Marco Tulio Ribeiro