A Comparison of Regularization Techniques for Shallow Neural Networks Trained on Small Datasets

Number of the records: 1

1.

SYSNO	0546161
Title	A Comparison of Regularization Techniques for Shallow Neural Networks Trained on Small Datasets
Author(s)	Tumpach, Jiří (UIVT-O)_{ORCID, SAI} Kalina, Jan (UIVT-O)_{RID, SAI, ORCID} Holeňa, Martin (UIVT-O)_{SAI, RID}
Source Title	Proceedings of the 21st Conference Information Technologies – Applications and Theory (ITAT 2021). S. 94-103. - Aachen : Technical University & CreateSpace Independent Publishing, 2021 / Brejová B. ; Ciencialová L. ; Holeňa M. ; Mráz F. ; Pardubská D. ; Plátek M. ; Vinař T.
Conference	ITAT 2021: Information Technologies - Applications and Theory /21./, 24.09.2021 - 28.09.2021, Heľpa
Document Type	Konferenční příspěvek (zahraniční konf.)
Grant	GA18-18080S GA ČR - Czech Science Foundation (CSF), CZ - Czech Republic
	GA19-05704S GA ČR - Czech Science Foundation (CSF), CZ - Czech Republic
	LM2018140, CZ - Czech Republic
Institutional support	UIVT-O - RVO:67985807
Language	eng
Country	DE
Keywords	artificial neural networks * regularization * robustness * optimization
Cooperating institutions	Matematicko-fyzikalni fakulta UK
URL	https://ics.upjs.sk/~antoni/ceur-ws.org/Vol-0000/paper38.pdf
Permanent Link	http://hdl.handle.net/11104/0322710

	File	Download	Size	Commentary	Version	Access
	0546161-aoa.pdf	1	6.1 MB	OA CC BY 4.0	Publisher’s postprint	open-access

Number of the records: 1