In this seminar, we will focus on the challenges in the design of safe and verified AI-based systems. We will explore some of the major problems in this area from the viewpoint of industry and academia. We plan to have a weekly seminar speaker to discuss issues such as safety, fairness, verification of AI systems, reward misalignment and hacking, secure and attack-resilient AI systems, diagnosis and repair, issues regarding policy and ethics, as well as the implications of AI safety in automotive industry.
We plan to take attendance using Google forms starting from the second week. If you are taking the class for credit, you need to attend 6 out of 8 talks.
Date | Speaker | Details |
---|---|---|
March 30 | Timnit Gebru, Google
|
Talk Title TBD
Bio: |
April 6 | Daniel Dewey, Open Philanthropy
|
Talk Title TBD
Bio: |
April 13 | Siddhartha Srinivasa, UW and Amazon Robotics
|
Talk Title TBD
Bio: |
May 4 | Zico Kolter, Carnegie Mellon University
|
Talk Title TBD
Bio: |
May 18 | Nika Haghtalab, Cornell University
|
Talk Title TBD
Bio: |
© Dorsa Sadigh 2020