Why is Everyone Training Very Deep Neural Network with Skip Connections?

Reference : Why is Everyone Training Very Deep Neural Network with Skip Connections?


	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Security, Reliability and Trust
	To cite this reference:	http://hdl.handle.net/10993/48927

Title :	Why is Everyone Training Very Deep Neural Network with Skip Connections?
Language :	English
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 >]
Publication date :	24-Nov-2021
Journal title :	IEEE Transactions on Neural Networks and Learning Systems
Publisher :	IEEE Computational Intelligence Society
Peer reviewed :	Yes
ISSN :	2162-237X
Country :	United States
Keywords :	[en] Very deep neural network ; skip connection ; optimization ; generalization
Permalink :	http://hdl.handle.net/10993/48927
FnR project :	FnR ; FNR11295431 > Oyebade Oyedotun > AVR > Automatic Feature Selection For Visual Recognition > 01/02/2017 > 31/01/2021 > 2016

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	TNNLS-2020-P-13752.pdf		Author preprint	4.35 MB	View/Open

All documents in ORBi^lu are protected by a user license.