In this paper, the steady-state performance of the distributed least mean-squares (dLMS) algorithm within an incremental network is evaluated without the restriction of Gaussian distributed inputs. Computer simulations are presented to verify the derived performance expressions.
Title
Steady-state performance of incremental learning over distributed networks for non-Gaussian data
Published in
9th International Conference on Signal Processing
Pages
227-230
Conference
9th International Conference on Signal Processing (ICSP 2008), Beijing, China, October 26-29, 2008
Date
2008
Publisher
IEEE
Record creation date
2017-12-19