Since (Not If) AIs Will Rule Us, Let's Make Them Nice To Us

Dr. Ian Davidson
Professor of Computer Science, University of California - Davis

Salazar Hall 2009A
4:00 PM - 5:00 PM

Abstract: It is inevitable that AIs will soon be making many life-altering decisions on us. Because of this, we need to ensure their behavior is guided by human values—a challenge widely known as the AI Alignment problem. I'll discuss our work on fairness and explanation alignment, presenting both theoretical and experimental results developed with collaborators, particularly our medical center. Our research has focused on classic tasks like outlier detection, classification and clustering for images, as well as more recent work involving large language models. Underlying this research is a common fundamental set of questions of how to encode constraints and extract constraints into/from deep learning. I'll conclude by discussing the need to explore alignment beyond fairness.

Bio: Prof. Ian Davidson has been a Professor of Computer Science and the University of California - Davis since 2007. In the 2000s he focused on adding constraints to machine learning algorithms particularly clustering, in the 2010s he focused on tensor decomposition and transfer learning. After a 2018 sabbatical stay in France (where someone asked him what was the ethical implications of his work) he has focused on making AIs more ethical. He also works with domain experts to apply his work to problems of social significance in particular neuroscience applications. This work is funded by gifts from Google and Intel and grants from the National Science Foundation (NSF), The Office of Naval Research (ONR) and The National Institute of Health (NIH).