Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition

Reference : Reducing overfitting and improving generalization in training convolutional neural ne...


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/45107

Title :	Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition
Language :	English
Author, co-author :	Thanapol, Panissara [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
	Lavangnananda, Kittichai [King Mongkut’s University of Technology Thonburi (Bangkok) > School of Information Technology]
	Bouvry, Pascal [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
	Pinel, Frederic [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
	Leprevost, Franck [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
Publication date :	2020
Main document title :	5th International Conference on Information Technology, Bangsaen 21-22 October 2020
Pages :	300-305
Peer reviewed :	Yes
On invitation :	No
Audience :	International
Event name :	5th International Conference on Information Technology - InCIT2020
Event date :	from 21-10-2020 to 22-10-2020
Event organizer :	Association of Council of IT Deans (CITT)
Event place (city) :	Bangsaen
Event country :	Thailand
Permalink :	http://hdl.handle.net/10993/45107

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	InCIT2020 Submission (Final Manuscript - IEEE eXpress checked) - Paper No. 1570661319.pdf		Publisher postprint	1.48 MB	View/Open

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