Article (Scientific journals)
Why is Everyone Training Very Deep Neural Network with Skip Connections?
Oyedotun, Oyebade; Al Ismaeil, Kassem; Aouada, Djamila
2021In IEEE Transactions on Neural Networks and Learning Systems
Peer Reviewed verified by ORBi
 

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



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)

Scopus citations®
 
8
Scopus citations®
without self-citations
8
WoS citations
 
9

Bibliography


Similar publications



Contact ORBilu