6.7960 | Fall 2024 | Undergraduate, Graduate

Deep Learning

Lec 03. Approximation Theory

How well can you approximate a given function by a DNN? We will explore various facets of this issue, from universal approximation to Barron’s theorem. And does increasing the depth provably help for expressivity?

Learning Resource Types
Lecture Notes
Lecture Videos
Problem Sets
Projects with Examples
Readings