Login
EN
[EN] English
[FR] Français
Login
EN
[EN] English
[FR] Français
Give us feedback
Search and explore
Search
Explore ORBilu
Open Science
Open Science
Open Access
Research Data Management
Definitions
Love My Data 11 - 15 Mar 2024
Statistics
Help
User Guide
FAQ
Publication list
Document types
Training
Legal Information
Data protection
Legal notices
About
About ORBilu
Deposit Mandate
ORBilu team
Impact and visibility
About statistics
About metrics
OAI-PMH
Project history
Back
Home
Detailled Reference
Download
Article (Scientific journals)
Why is Everyone Training Very Deep Neural Network with Skip Connections?
Oyedotun, Oyebade
;
Al Ismaeil, Kassem
;
Aouada, Djamila
2021
•
In
IEEE Transactions on Neural Networks and Learning Systems
Peer Reviewed verified by ORBi
Permalink
https://hdl.handle.net/10993/48927
DOI
10.1109/TNNLS.2021.3131813
PubMed
34986102
Files
Send to
Details
Statistics
Bibliography
Similar publications
Files
Full Text
TNNLS-2020-P-13752.pdf
Author preprint (4.45 MB)
Download
All documents in ORBilu are protected by a
user license
.
Send to
RIS
BibTex
APA
Chicago
Permalink
X
Linkedin
copy to clipboard
copied
Details
Keywords :
Very deep neural network; skip connection; optimization; generalization
Disciplines :
Computer science
Author, co-author :
Oyedotun, Oyebade
;
University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Al Ismaeil, Kassem
Aouada, Djamila
;
University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
no
Language :
English
Title :
Why is Everyone Training Very Deep Neural Network with Skip Connections?
Publication date :
24 November 2021
Journal title :
IEEE Transactions on Neural Networks and Learning Systems
ISSN :
2162-237X
eISSN :
2162-2388
Publisher :
IEEE Computational Intelligence Society, United States
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Security, Reliability and Trust
FnR Project :
FNR11295431 - Automatic Feature Selection For Visual Recognition, 2016 (01/02/2017-31/01/2021) - Oyebade Oyedotun
Available on ORBilu :
since 09 December 2021
Statistics
Number of views
83 (14 by Unilu)
Number of downloads
465 (17 by Unilu)
More statistics
Scopus citations
®
8
Scopus citations
®
without self-citations
8
WoS citations
™
9
Bibliography
Similar publications
Contact ORBilu