Deep ConvNet: Non-random weight initialization for repeatable determinism, examined with FSGM

Rudd-Orthner, R. orcid.org/0000-0002-2534-0920 and Mihaylova, L. (2021) Deep ConvNet: Non-random weight initialization for repeatable determinism, examined with FSGM. Sensors, 21 (14). 4772. ISSN 1424-8220

Abstract

Metadata

Authors/Creators:
Copyright, Publisher and Additional Information: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Keywords: repeatable determinism; weight initialization; convolutional layers; adversarial perturbation attack; FSGM; transferred learning; machine learning; smart sensors
Dates:
  • Accepted: 9 July 2021
  • Published (online): 13 July 2021
  • Published: 13 July 2021
Institution: The University of Sheffield
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield)
Depositing User: Symplectic Sheffield
Date Deposited: 16 Jul 2021 16:05
Last Modified: 16 Jul 2021 16:39
Status: Published
Publisher: MDPI AG
Refereed: Yes
Identification Number: https://doi.org/10.3390/s21144772
Related URLs:

Download

Share / Export

Statistics