Title :
Generalized eigendecomposition with an on-line local algorithm
Author :
Xu, Dongxin ; Principe, Jose C. ; Wu, Hsiao-Chun
Author_Institution :
Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA
Abstract :
This article presents a novel, on-line, local learning algorithm to obtain generalized eigenvalues and their corresponding eigenvectors in descending order with a linear adaptive filter. The filter is composed of a set of forward linear projections constrained by lateral inhibitions. Equilibrium points of the adaptation process and their stability are briefly analyzed. Simulations and experimental comparisons are given to verify the validity and effectiveness of the proposed algorithm.
Keywords :
Hebbian learning; adaptive filters; adaptive signal processing; eigenvalues and eigenfunctions; filtering theory; numerical stability; pattern recognition; Hebbian based adaptation; adaptation process; adaptive signal processing; anti-Hebbian based adaptation; eigenvectors; equilibrium points; experiment; forward linear projections; generalized eigendecomposition; generalized eigenvalues; lateral inhibitions; linear adaptive filter; local learning algorithm; on-line local algorithm; pattern recognition; simulations; stability; Adaptive filters; Convergence; Data compression; Decorrelation; Eigenvalues and eigenfunctions; Linear discriminant analysis; Nonlinear filters; Principal component analysis; Signal analysis; Stability analysis;
Journal_Title :
Signal Processing Letters, IEEE
