Deep neural networks are lazy : on the inductive bias of deep learning
Name
1102057114-MIT.pdf
Size
3.54 MB
Format
Adobe PDF
Checksum (MD5)
5762eb9bc5d060103f5cc6bb5e6abc89
Author(s)
Mansour, Tarek,M. Eng.Massachusetts Institute of Technology.
Advisor(s)
Aleksander Madry.
Alternative Title
On the inductive bias of deep learning
Date Issued
2019
Publisher
Massachusetts Institute of Technology
Abstract
Deep learning models exhibit superior generalization performance despite being heavily overparametrized. Although widely observed in practice, there is currently very little theoretical backing for such a phenomena. In this thesis, we propose a step forward towards understanding generalization in deep learning. We present evidence that deep neural networks have an inherent inductive bias that makes them inclined to learn generalizable hypotheses and avoid memorization. In this respect, we propose results that suggest that the inductive bias stems from neural networks being lazy: they tend to learn simpler rules first. We also propose a definition of simplicity in deep learning based on the implicit priors ingrained in deep neural networks.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 75-78).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
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.
Persistent DSpace Link
