Yonatan Kahn is a theoretical physicist studying dark matter and its detection strategies, as well as the theory of machine learning from a high-energy physics perspective. Currently an assistant professor of physics at University of Toronto, he previously held postdoctoral positions at the Kavli Institute for Cosmological Physics (KICP) at the University of Chicago and Princeton University, as well as a faculty position at University of Illinois Urbana-Champaign. His machine learning research focuses on deep learning theory using calculational tools from high-energy physics (“HEP for AI”), as well as uncertainty quantification.
Assistant Professor, University of Toronto
Research Interests
- Bayesian Methods
- Deep Learning
- Physics
Highlights
- 2022: Kavli Frontiers of Science Fellow, National Academy of Sciences
- 2022: PI of US $268K grant, “Uncertainty Quantification from Neural Network Correlation Functions” (US Department of Energy)