Treffer: Fast Adaptive Extraction Algorithm for Multiple Principal Generalized Eigenvectors

Title:
Fast Adaptive Extraction Algorithm for Multiple Principal Generalized Eigenvectors
Source:
Recent Advances in Intelligent TechniquesInternational journal of intelligent systems. 28(3):289-306
Publisher Information:
Hoboken, NJ: Wiley, 2013.
Publication Year:
2013
Physical Description:
print, 27 ref
Original Material:
INIST-CNRS
Document Type:
Fachzeitschrift Article
File Description:
text
Language:
English
Author Affiliations:
Department of Automation, University of Science and Technology of China, Hefei, Anhui 230027, China
ISSN:
0884-8173
Rights:
Copyright 2014 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Mathematics
Accession Number:
edscal.27283771
Database:
PASCAL Archive

Weitere Informationen

We consider adaptively extracting multiple principal generalized eigenvectors, which can be widely applied in modern signal processing. By using the deflation technique, the problem is reformulated into an unconstrained minimization problem. An adaptive sequential algorithm based on the Newton method is proposed to solve this problem. To improve its real-time performance, a parallel version of this algorithm is provided on the basis of certain approximation. Furthermore, a two-layer neural network is constructed to execute the adaptive algorithm. The asymptotic convergence of this algorithm is rigorously proved by stochastic approximation theory. The simulation results demonstrate the effectiveness of the proposed algorithms.