On the relation between neural network size and performance

Author(s)
Rosenfeld, Jonathan S.(Jonathan Shmuel)
Thumbnail
Download1124957898-MIT.pdf (2.790Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Nir Shavit.
Terms of use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582
Metadata
Show full item record
Abstract
Artificial Neural Networks (NN) are notorious for their size requirements and for the effort involved in developing well performing network models. This thesis uncovers a fundamental relationship that ties model size and performance in a predictable manner. This relationship enables a well-founded development of networks at small scale while producing insight into their large-scale behavior.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
 
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
 
Cataloged from student-submitted PDF version of thesis.
 
Includes bibliographical references (pages 57-58).
 
Date issued
2019
URI
https://hdl.handle.net/1721.1/122703
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.
Collections