Why do Deep Neural Networks with Skip Connections and Concatenated Hidden Representations Work?

Reference : Why do Deep Neural Networks with Skip Connections and Concatenated Hidden Representat...


	Document type :	Scientific congresses, symposiums and conference proceedings : Poster
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/44452

Title :	Why do Deep Neural Networks with Skip Connections and Concatenated Hidden Representations Work?
Language :	English
Author, co-author :	Oyedotun, Oyebade [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 >]
Publication date :	18-Nov-2020
Peer reviewed :	Yes
Event name :	The 27th International Conference on Neural Information Processing (ICONIP2020)
Event date :	18-11-2020 to 22-11-2020
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Funders :	Fonds National de la Recherche - FnR
Permalink :	http://hdl.handle.net/10993/44452
FnR project :	FnR ; FNR11295431 > Oyebade Oyedotun > > 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	OyedotunAouada_ICONIP2020_full paper.pdf		Author postprint	2.08 MB	View/Open

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