Description

This seminar will explore the challenges in designing and testing safe AI-based systems. Each week we will have a speaker from industry or academia discuss one problem area in AI safety. Our speakers will discuss issues such as verification and validation of AI systems, robustness, reward misspecification and hacking, explainbabililty of black-box models, AI ethics, and AI governence. Application areas will include transportation, natural language processing, and medicine.

Attendance

If you are taking the class for credit, you need to attend 7 out of 10 talks. Please record your attendance here and let the course staff know if you have a conflict, illness, etc and cannot attend in person. For the in-person talks, no recording will be available since the course room is not outfitted to record.