Non-random weight initialisation in deep learning networks for repeatable determinism

Rudd-Orthner, R. and Mihaylova, L. (2019) Non-random weight initialisation in deep learning networks for repeatable determinism. In: 2019 IEEE 10th International Conference on Dependable Systems, Services and Technologies (DESSERT). 10th International Conference Dependable Systems, Services and Technologies, 05-07 Jun 2019, Leeds, United Kingdom. IEEE . ISBN 9781728117348

Abstract

Metadata

Authors/Creators:
  • Rudd-Orthner, R.
  • Mihaylova, L.
Copyright, Publisher and Additional Information: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy.
Keywords: Deep learning; Safety; Mission critical systems; Task analysis; Fitting
Dates:
  • Accepted: 12 April 2019
  • Published (online): 25 July 2019
  • Published: 7 June 2019
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: 28 May 2019 11:48
Last Modified: 25 Jul 2020 00:38
Status: Published
Publisher: IEEE
Refereed: Yes
Identification Number: https://doi.org/10.1109/DESSERT.2019.8770007

Export

Statistics