Back to research teams

AI Safety team at the Centre for Mathematical AI at Fields Institute for Mathematics

Active

Research focus

Developing rigorous mathematical foundations for AI interpretability. Research directions include mean field theories of deep learning, data attribution methods, renormalization group approaches to neural networks, learning-theoretic analysis of algorithms and geometric analysis of the learning landscape.

Open to collaboration
Yes
Looking for

Postdoctoral fellows

Join the Damaqu community to see this team's full profile.
AI Safety team at the Centre for Mathematical AI at Fields Institute for Mathematics — Damaqu