Published February 2, 2020
| public
Book Section - Chapter
Improve Robustness of Deep Neural Networks by Coding
Abstract
Deep neural networks (DNNs) typically have many weights. When errors appear in their weights, which are usually stored in non-volatile memories, their performance can degrade significantly. We review two recently presented approaches that improve the robustness of DNNs in complementary ways. In the first approach, we use error-correcting codes as external redundancy to protect the weights from errors. A deep reinforcement learning algorithm is used to optimize the redundancy-performance tradeoff. In the second approach, internal redundancy is added to neurons via coding. It enables neurons to perform robust inference in noisy environments.
Additional Information
© 2020 IEEE.Additional details
- Eprint ID
- 106993
- DOI
- 10.1109/ita50056.2020.9244998
- Resolver ID
- CaltechAUTHORS:20201209-153308085
- Created
-
2020-12-10Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field