Spring 2026 GRASP on Robotics: Daniel Lee, Cornell University, “AI White Boxes and Neural Representation Geometry”
February 27 at 10:30 AM - 11:45 AM
This event will be in-person ONLY in Wu and Chen Auditorium.
ABSTRACT
Black box methods such as the Turing Test are no longer adequate for evaluating AI models. Quantifying the structure and similarity of high-dimensional neural representations are essential for better understanding and training of large neural network models. Statistical insights can be gained by analyzing the geometrical structure of these representations as they are reformatted by neural network hierarchies. Unfortunately, conventional analysis based upon covariance matrices yield biased estimators under realistic constraints of finite data. I will present some recent advances in developing efficient estimators that address these limitations. Our results highlight the importance of developing principled statistical tools to analyze neural representations.
Daniel Lee
Cornell University
Dr. Daniel D. Lee is the Tisch University Professor in Electrical and Computer Engineering at Cornell University. He previously worked at Bell Labs, University of Pennsylvania, and Samsung Electronics. He is a visiting scholar at the Korea Institute of Advanced Studies (KIAS) and at the Flatiron Institute, Simons Foundation, in New York City. He is also a Fellow of the IEEE and AAAI and has received the NSF CAREER award and the Lindback award for distinguished teaching. His group focuses on understanding general computational principles in biological systems and on applying that knowledge to build autonomous systems.