Skip to content

Proof of a Universal Approximation Theorem for ReLU based Neural Networks and An Empirical Investigation of the Resulting Bound

Notifications You must be signed in to change notification settings

NicholasJohnson2020/ReLU-NN-Function-Approximation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

ReLU-NN-Function-Approximation

Proof of a Universal Approximation Theorem for ReLU based Neural Networks and An Empirical Investigation of the Resulting Bound

In collaboration with Teodor-Andrei Andronache and Paula Gradu.

This is my capstone project for the class COS 511: Theoretical Machine Learning at Princeton University. Course description here: https://www.cs.princeton.edu/courses/archive/spring19/cos511/

About

Proof of a Universal Approximation Theorem for ReLU based Neural Networks and An Empirical Investigation of the Resulting Bound

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published