Please use this identifier to cite or link to this item:
Title: Stochastic dynamics of neural networks after learning
Authors: Kapelko, V. V.
Linkevich, A. D.
Keywords: Математическая кибернетика
нейронные сети
динамические модели
Issue Date: Dec-2011
Publisher: Полоцкий государственный университет
Citation: Вестник Полоцкого государственного университета. Серия C, Фундаментальные науки: научно-теоретический журнал.- Новополоцк : ПГУ, 2011.- № 12.- С. 16-18
Series/Report no.: Серия C, Фундаментальные науки;2011. - № 12
Abstract: We study probabilistic synchronous dynamics of Little-Hopfield neural networks with asymmetric interneuronal synaptic connections adjusted in accordance with a learning rule given in [3]. Types of behaviour of such systems are analysed in dependence of a vector-parameter characterizing degrees of freedom in determining synaptic couplings. We have found that in the case of small level of noise networks can store memorized patterns but as an amount of noise is increased behaviour becomes more complex and, beginning with some critical value the motion seems to be chaotic.
Appears in Collections:2011, № 12

Files in This Item:
File Description SizeFormat 
Kapelko_2011-12-p16.pdf207.74 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.