eduzhai > Applied Sciences > Engineering >

Combined Sparse Regularization for Nonlinear Adaptive Filters

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Nonlinear adaptive filters often show some sparse behavior due to the factthat not all the coefficients are equally useful for the modeling of anynonlinearity. Recently, a class of proportionate algorithms has been proposedfor nonlinear filters to leverage sparsity of their coefficients. However, thechoice of the norm penalty of the cost function may be not always appropriatedepending on the problem. In this paper, we introduce an adaptive combinedscheme based on a block-based approach involving two nonlinear filters withdifferent regularization that allows to achieve always superior performancethan individual rules. The proposed method is assessed in nonlinear systemidentification problems, showing its effectiveness in taking advantage of theonline combined regularization.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...