Please use this identifier to cite or link to this item:
Title: Stability and chaos of a class of learning algorithms for ICA neural networks
Authors: Lv, J.C.
Tan, K.K. 
Yi, Z.
Huang, S. 
Keywords: Bifurcation and chaos
Dynamical behavior
Independent component analysis
Lyapunov exponents
Issue Date: Aug-2008
Citation: Lv, J.C., Tan, K.K., Yi, Z., Huang, S. (2008-08). Stability and chaos of a class of learning algorithms for ICA neural networks. Neural Processing Letters 28 (1) : 35-47. ScholarBank@NUS Repository.
Abstract: Independent component analysis (ICA) neural networks can estimate independent components from the mixed signal. The dynamical behavior of the learning algorithms for ICA neural networks is crucial to effectively apply these networks to practical applications. The paper presents the stability and chaotic dynamical behavior of a class of ICA learning algorithms with constant learning rates. Some invariant sets are obtained so that the non-divergence of these algorithms can be guaranteed. In these invariant sets, the stability and chaotic behaviors are analyzed. The conditions for stability and chaos are derived. Lyapunov exponents and bifurcation diagrams are presented to illustrate the existence of chaotic behavior. © 2008 Springer Science+Business Media, LLC.
Source Title: Neural Processing Letters
ISSN: 13704621
DOI: 10.1007/s11063-008-9080-2
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Jan 24, 2020


checked on Jan 16, 2020

Page view(s)

checked on Jan 28, 2020

Google ScholarTM



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