Back
  1. Home
  3. Detailled Reference
Download
Article (Scientific journals)
Training very deep neural networks: Rethinking the role of skip connections
Oyedotun, Oyebade; Al Ismaeil, Kassem; Aouada, Djamila
2021 • In Neurocomputing
Peer Reviewed verified by ORBi
Permalink
https://hdl.handle.net/10993/47494
DOI
10.1016/j.neucom.2021.02.004
 

Files (1)Send toDetailsStatisticsBibliographySimilar publications

Files

Full Text
OyedotunAl IsmaeilAouada_NeurocomputingJournal.pdf
Author preprint (1.29 MB)
Download

All documents in ORBilu are protected by a user license.

Send to


Details


Keywords :
Deep neural network; Residual learning; Skip connection; Optimization
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Disciplines :
Computer science
Author, co-author :
Oyedotun, Oyebade ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Al Ismaeil, Kassem ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
no
Language :
English
Title :
Training very deep neural networks: Rethinking the role of skip connections
Publication date :
21 June 2021
Journal title :
Neurocomputing
ISSN :
0925-2312
Publisher :
Elsevier, Amsterdam, Netherlands
Peer reviewed :
Peer Reviewed verified by ORBi
FnR Project :
FNR11295431 - Automatic Feature Selection For Visual Recognition, 2016 (01/02/2017-31/01/2021) - Oyebade Oyedotun
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 20 June 2021

Statistics

Number of views
265 (18 by Unilu)
Number of downloads
315 (7 by Unilu)
More statistics
Scopus citations®
 
8
Scopus citations®
without self-citations
8
OpenCitations
 
2
WoS citations™
 
6

Bibliography

Similar publications


Contact ORBilu