An Overview of Some Issues in the Theory of Deep Networks
Name
New_ieej__long_ver16.pdf
Description
Accepted version
Size
5.81 MB
Format
Unknown
Checksum (MD5)
56d6796408e5dadcc110875c3162c21e
Author(s)
Poggio, Tomaso
Banburski, Andrzej
Date Issued
October 2020
Journal
IEEJ Transactions on Electrical and Electronic Engineering
Publisher
Wiley
Citation
Poggio, Tomaso and Banburski, Andrzej. 2020. "An Overview of Some Issues in the Theory of Deep Networks." IEEJ Transactions on Electrical and Electronic Engineering, 15 (11).
Version
Author's final manuscript
Abstract
© 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. During the last few years, significant progress has been made in the theoretical understanding of deep networks. We review our contributions in the areas of approximation theory and optimization. We also introduce a new approach based on cross-validation leave-one-out stability to estimate bounds on the expected error of overparametrized classifiers, such as deep networks. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.
MIT Department
Center for Brains, Minds, and Machines
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1002/tee.23243
