About the Group

This reading group explores technical and philosophical works on Trustworthy AI. Trustworthy AI considers how to build AI sytems that are robust, secure, transparent, and fair. We condsider work from many angles including the following:

• Causality
• Robustness
• Security and Privacy
• Intepretability and Explainability
• Fairness
• AI Ethics

If you are interested in these areas please consider joining us for a reading group. All experience levels are welcome.

Conduct

We encourage open discussion! Any and all questions are welcome. To best facilitate this our meetings are not recorded and are coducted with the expectation of confidentiality. We highly recommend checking out some conduct rules we have adopted from another reading group, the ML Collective.