Title :
Gradient-based adaptive algorithm with an optimum vector of convergence factors
Author :
Ghavami, Mohammad ; Rupprecht, Werner ; Nader-Esfahani, Said
Author_Institution :
Dept. of Electr. Eng., Univ. of Sci. & Defense Technol., Shahin Shahr, Iran
fDate :
12/1/1995 12:00:00 AM
Abstract :
An alternative perspective of adaptive filtering by way of optimization theory is presented. We derive an optimum vector of convergence factors for a general-structure adaptive filter and the gradient algorithm. It is proved that the optimum vector of convergence factors produces a faster convergence compared with the optimum but single convergence factor
Keywords :
adaptive filters; adaptive signal processing; circuit optimisation; convergence of numerical methods; filtering theory; least mean squares methods; vectors; LMS algorithm; adaptive filtering; convergence factors; general-structure adaptive filter; gradient algorithm; gradient-based adaptive algorithm; optimization theory; optimum vector; Adaptive algorithm; Adaptive filters; Biomedical signal processing; Convergence; Discrete cosine transforms; Electrocardiography; Finite impulse response filter; IIR filters; Image reconstruction; Signal resolution;
Journal_Title :
Signal Processing, IEEE Transactions on
