Abstract | ||
---|---|---|
In this work, we propose a novel LMS type algorithm by utilizing the q-gradient. The concept of q-gradient is derived from the definition of Jacksons derivative which is also called as the q-derivative. The q-gradient based LMS algorithm results in faster convergence for q > 1 because of the fact that the q-derivative, unlike the conventional derivative which evaluates tangent, computes the secant of the cost function and hence takes larger steps towards the optimum solution. We show an important application of the proposed q-LMS algorithm in which it acts like a whitening filter. Convergence analysis of the proposed algorithm is also presented. Simulation results are presented to support our theoretical findings. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ACSSC.2014.7094580 | Pacific Grove, CA |
Keywords | Field | DocType |
convergence of numerical methods,filtering theory,gradient methods,least mean squares methods,Jacksons derivative,convergence analysis,cost function,least mean squares algorithm,optimum solution,q-derivative,q-gradient based LMS algorithm,whitening filter,Convergence analysis,LMS algorithm,q-LMS algorithm,q-gradient | Convergence (routing),Least mean squares filter,Mathematical optimization,Whitening filter,Least mean square algorithm,Tangent,Recursive least squares filter,Mathematics | Conference |
ISSN | Citations | PageRank |
1058-6393 | 1 | 0.36 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ubaid M. Al-Saggaf | 1 | 37 | 9.76 |
Muhammad Moinuddin | 2 | 8 | 1.92 |
Azzedine Zerguine | 3 | 343 | 51.98 |