Improving nonlinear modeling capabilities of functional link adaptive filters

Danilo Comminiello; Michele Scarpiniti; Simone Scardapane; Raffaele Parisi; Aurelio Uncini

doi:10.1016/j.neunet.2015.05.002

Improving nonlinear modeling capabilities of functional link adaptive filters

Neural Netw. 2015 Sep:69:51-9. doi: 10.1016/j.neunet.2015.05.002. Epub 2015 May 27.

Authors

Danilo Comminiello¹, Michele Scarpiniti², Simone Scardapane², Raffaele Parisi², Aurelio Uncini²

Affiliations

¹ Department of Information Engineering, Electronics and Telecommunications (DIET), "Sapienza" University of Rome, Via Eudossiana 18, 00184 Rome, Italy. Electronic address: danilo.comminiello@uniroma1.it.
² Department of Information Engineering, Electronics and Telecommunications (DIET), "Sapienza" University of Rome, Via Eudossiana 18, 00184 Rome, Italy.

PMID: 26057613
DOI: 10.1016/j.neunet.2015.05.002

Abstract

The functional link adaptive filter (FLAF) represents an effective solution for online nonlinear modeling problems. In this paper, we take into account a FLAF-based architecture, which separates the adaptation of linear and nonlinear elements, and we focus on the nonlinear branch to improve the modeling performance. In particular, we propose a new model that involves an adaptive combination of filters downstream of the nonlinear expansion. Such combination leads to a cooperative behavior of the whole architecture, thus yielding a performance improvement, particularly in the presence of strong nonlinearities. An advanced architecture is also proposed involving the adaptive combination of multiple filters on the nonlinear branch. The proposed models are assessed in different nonlinear modeling problems, in which their effectiveness and capabilities are shown.

Keywords: Adaptive combination of filters; Functional links; Nonlinear modeling; Online learning algorithms.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Humans
Models, Theoretical
Neural Networks, Computer*
Nonlinear Dynamics*