Stanford University

SEMINAR SERIES

Max Tegmark | Towards Understanding Grokking: An Effective Theory of Representation Learning

Max Tegmark | Towards Understanding Grokking: An Effective Theory of Representation Learning
October 17, 2022
12p - 1p Pacific Time
Virtual event
Free
Register
Show buttons

Join us on October 17, 2022, when MIT’s Max Tegmark talks about “Understanding Grokking: An Effective Theory of Representation Learning.” More information about this event will be posted soon.

This is a free virtual event open to everyone.


Abstract

Abstract to come.


About Max Tegmark

Max Tegmark’s research is focused on precision cosmology, e.g., combining theoretical work with new measurements to place sharp constraints on cosmological models and their free parameters. During his first quarter-century as a physics researcher, this criterion has lead him to work mainly on cosmology and quantum information. Although he’s continuing his cosmology work with the HERA collaboration, the main focus of his current research is on the physics of intelligence: using physics-based techniques to better understand biological and artificial intelligence (AI).

Stanford University