Comparing the efficiency of serial and parallel algorithms for training artificial neural networks using computer clusters

An estimation of the number of multiplication and addition operations for training artififfcial neural networks by means of consecutive and parallel algorithms on a computer cluster is carried out. The evaluation of the efficiency of these algorithms is developed. The multilayer perceptron, the Volterra network and the cascade-correlation network are used as structures of artififfcial neural networks. Different methods of non-linear programming such as gradient and non-gradient methods are used for the calculation of the weight coefficients.

Metadaten
Author:	Oleg V. Kryuchin, Alexander A. Arzamastsev, Klaus G. Troitzsch
URN:	urn:nbn:de:kola-5602
Series (Volume no.):	Arbeitsberichte, FB Informatik (2011,13)
Document Type:	Part of Periodical
Language:	English
Date of completion:	2011/09/29
Date of publication:	2011/09/29
Publishing institution:	Universität Koblenz-Landau, Campus Koblenz, Universitätsbibliothek
Release Date:	2011/09/29
Tag:	artififfcial neural networks; computer clusters; estimation of algorithm efficiency; parallel algorithms
Number of pages:	30 Seiten
Institutes:	Fachbereich 4 / Fachbereich 4
	Fachbereich 4 / Institut für Wirtschafts- und Verwaltungsinformatik
Dewey Decimal Classification:	0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):	Es gilt das deutsche Urheberrecht: § 53 UrhG