A weight perturbation-based regularisation technique for convolutional neural networks and the application in medical imaging

Khatami, Amin, Nazari, Asef, Khosravi, Abbas, Lim, Chee Peng and Nahavandi, Saeid 2020, A weight perturbation-based regularisation technique for convolutional neural networks and the application in medical imaging, Expert systems with applications, vol. 149, pp. 1-8, doi: 10.1016/j.eswa.2020.113196.

Attached Files
Name Description MIMEType Size Downloads

Title A weight perturbation-based regularisation technique for convolutional neural networks and the application in medical imaging
Author(s) Khatami, Amin
Nazari, AsefORCID iD for Nazari, Asef orcid.org/0000-0003-4955-9684
Khosravi, AbbasORCID iD for Khosravi, Abbas orcid.org/0000-0001-6927-0744
Lim, Chee PengORCID iD for Lim, Chee Peng orcid.org/0000-0003-4191-9083
Nahavandi, SaeidORCID iD for Nahavandi, Saeid orcid.org/0000-0002-0360-5270
Journal name Expert systems with applications
Volume number 149
Article ID 113196
Start page 1
End page 8
Total pages 8
Publisher Elsevier
Place of publication Amsterdam, The Netherlands
Publication date 2020
ISSN 0957-4174
Keyword(s) Convolutional Neural Network
Regularisation
Generalisation
Weight perturbation
Language eng
DOI 10.1016/j.eswa.2020.113196
Indigenous content off
Field of Research 01 Mathematical Sciences
08 Information and Computing Sciences
HERDC Research category C1 Refereed article in a scholarly journal
Free to Read? No
Free to Read Start Date 2022-07-02
Persistent URL http://hdl.handle.net/10536/DRO/DU:30135168

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 2 times in TR Web of Science
Scopus Citation Count Cited 3 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 85 Abstract Views, 5 File Downloads  -  Detailed Statistics
Created: Thu, 20 Feb 2020, 10:47:31 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.