University of Cambridge > > Engineering Safe AI > Interpretable Machine Learning

Interpretable Machine Learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Adrià Garriga Alonso.

How can we design AI systems that reliably act according to the true intent of their users, even as the capability of the systems increases?

This week we will read “Towards a Rigorous Science of Interpretable Machine Learning”, by Finale Doshi-Velez and Been Kim ; and if there’s time, “Challenges for Transparency” by Adrian Weller. Dr. Tameem Adel, a researcher in the Machine Learning Group who works in interpretability, will lead the discussion.

Doshi-Velez and Kim argue that interpretable machine learning is helpful to verify other properties of the system, when these properties are difficult to state formally. Verifying informal properties is likely to be a component of ensuring a system is value aligned, so it is interesting to know about this approach to the problem. Weller provides a counterpoint, detailing situations where interpretability is actually harmful, and also challenges to actually achieving it in different situations.

There will be free pizza. At 17:00, we will start reading the paper, mostly individually. At 17:30, the discussion leader will start going through the paper, making sure everyone understands, and encouraging discussion about its contents and implications.

Even if you think you cannot contribute to the conversation, you should give it a try. Last year we had several people from non-computer-y backgrounds, and others who hadn’t thought about alignment before, that ended up being essential. If you have already read the paper in your own time you can come in time for the discussion.

A basic understanding of machine learning is helpful, but detailed knowledge of the latest techniques is not required. Each session will have a brief recap of immediate necessary knowledge. The goal of this series is to get people to know more about the existing work in AI research, and eventually contribute to the field.

Invite your friends to join the mailing list (, the Facebook group ( or the page ( Details about the next meeting, the week’s topic and other events will be advertised in these places.

This talk is part of the Engineering Safe AI series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity