|
Sibirskii Zhurnal Vychislitel'noi Matematiki, 2013, Volume 16, Number 1, Pages 1–9
(Mi sjvm493)
|
|
|
|
Theorem of training for a competition algorithm
V. S. Antyufeev Institute of Computational Mathematics and Mathematical Geophysics (Computing Center), Siberian Branch of the Russian Academy of Sciences, Novosibirsk
Abstract:
This paper is an extension of [1], where a new decision algorithm was proposed. In its operation, the unit resembles artificial neural networks. However the functioning of the algorithm proposed is based on the different concepts. It does not use the concept of a net, a neuron. The theorem of training for the new competition algorithm is proved.
Key words:
theorem of training, probabilistic convergence, artificial neural network.
Received: 17.11.2011 Revised: 16.12.2011
Citation:
V. S. Antyufeev, “Theorem of training for a competition algorithm”, Sib. Zh. Vychisl. Mat., 16:1 (2013), 1–9; Num. Anal. Appl., 6:1 (2013), 1–8
Linking options:
https://www.mathnet.ru/eng/sjvm493 https://www.mathnet.ru/eng/sjvm/v16/i1/p1
|
Statistics & downloads: |
Abstract page: | 384 | Full-text PDF : | 121 | References: | 76 | First page: | 8 |
|