Presenter Information

Indupama Herath, Mathematics

Abstract

We show that sums of separable functions achieve similar error bound as single layer neural networks for functions in Barron’s space.

Keywords:

Artificial neural networks, Sums of separable functions, approximation power, Barron's space, mathematics

Status

Graduate

Department

Mathematics

College

College of Arts and Sciences

Campus

Athens

Faculty Mentor

Mohlenkamp, Dr. Martin J.

Share

COinS
 

Approximation of functions in Barron’s space using sums of separable functions.

We show that sums of separable functions achieve similar error bound as single layer neural networks for functions in Barron’s space.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.