Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

Asymptotics of sequential learning processes for neural networks in stochastic environment: special case

Azarskov V. N.  (National Aviation University (Kiev))

Zhiteckii L. S.  (National Aviation University (Kiev))

Nikolaienko S. A.  (Int. Research and Training Center for Inform. Technologies & Systems (Kiev) )

Asymptotical properties of the standard gradient algorithms for sequential learning in neural network models working in the stochastic environment for a special case, when the exact identification of an unknown nonlinearity is admissible, are studied. The sufficient convergence conditions of these algorithms are established. Simulation results are given.

Keywords:modern control theory, identification, nonlinearity, gradient algorithm, convergence, neural network, sequential learning
 

Read the full article …

Citation link:
Azarskov V. N., Zhiteckii L. S., Nikolaienko S. A. Asymptotics of sequential learning processes for neural networks in stochastic environment: special case // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2014. -№05-06. -С. 21-28
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences