Incorporating the Barzilai-Borwein adaptive step size into sugradient methods for deep network training

Robles-Kelly, Antonio and Nazari, Asef 2019, Incorporating the Barzilai-Borwein adaptive step size into sugradient methods for deep network training, in DICTA 2019 : Proceedings of the 2019 Digital Image Computing Techniques and Applications International Conference, IEEE, Piscataway, N.J., pp. 1-6, doi: 10.1109/DICTA47822.2019.8945980.

Attached Files
Name Description MIMEType Size Downloads

Title Incorporating the Barzilai-Borwein adaptive step size into sugradient methods for deep network training
Author(s) Robles-Kelly, AntonioORCID iD for Robles-Kelly, Antonio orcid.org/0000-0002-2465-5971
Nazari, AsefORCID iD for Nazari, Asef orcid.org/0000-0003-4955-9684
Conference name Digital Image Computing Techniques and Applications. International Conference (2019 : Perth, W.A.)
Conference location Perth, W.A.
Conference dates 2019/12/02 - 2019/12/04
Title of proceedings DICTA 2019 : Proceedings of the 2019 Digital Image Computing Techniques and Applications International Conference
Editor(s) Unknown
Publication date 2019
Start page 1
End page 6
Total pages 6
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) CORE Australasian
ISBN 9781728138572
Language eng
DOI 10.1109/DICTA47822.2019.8945980
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30135155

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 19 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Thu, 20 Feb 2020, 11:29:32 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.