• Deutsch
Login

OPUS

  • Home
  • Search
  • Browse
  • Publish
  • FAQ

Refine

Author

  • Arzamastsev, Alexander A. (3)
  • Kryuchin, Oleg V. (3)
  • Troitzsch, Klaus G. (3)

Year of publication

  • 2011 (3) (remove)

Language

  • English (2)
  • German (1)

Has Fulltext

  • yes (3) (remove)

Keywords

  • parallel algorithms (3) (remove)

Institute

  • Fachbereich 4 (3)
  • Institut für Wirtschafts- und Verwaltungsinformatik (3)

3 search hits

  • 1 to 3
  • 10
  • 20
  • 50
  • 100

Sort by

  • Year
  • Year
  • Title
  • Title
  • Author
  • Author
A universal simulator based on artificial neural networks for computer clusters (2011)
Kryuchin, Oleg V. ; Arzamastsev, Alexander A. ; Troitzsch, Klaus G.
This paper describes parallel algorithms for training artifcial neural networks. Possible levels of parallelity are presented. Experiments for checking the effciency of algorithms are discussed.
A parallel algorithm for selecting activation functions of an artificial network (2011)
Kryuchin, Oleg V. ; Arzamastsev, Alexander A. ; Troitzsch, Klaus G.
This paper describes a parallel algorithm for selecting activation functionsrnof an artifcial network. For checking the efficiency of this algorithm a count of multiplicative and additive operations is used.
Comparing the efficiency of serial and parallel algorithms for training artificial neural networks using computer clusters (2011)
Kryuchin, Oleg V. ; Arzamastsev, Alexander A. ; Troitzsch, Klaus G.
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.
  • 1 to 3

OPUS4 Logo

  • Contact
  • Imprint
  • Sitelinks