Sequential blind signal extraction in order specified by stochastic properties

A. Cichocki, R. Thawonmas, S. Amari

Research output: Contribution to journalArticlepeer-review

107 Citations (Scopus)

Abstract

A new neural-network adaptive algorithm is proposed for performing extraction of independent source signals from a linear mixture of them. Using a suitable nonlinear Hebbian learning rule and a new deflation technique, the developed neural network is able to extract the source signals (sub-Gaussian and/or super-Gaussian) one-by-one with specified order according to their stochastic properties, namely, in decreasing order of absolute normalised kurtosis. The validity and performance of the algorithm are confirmed through extensive computer simulations.

Original languageEnglish
Pages (from-to)64-65
Number of pages2
JournalElectronics Letters
Volume33
Issue number1
DOIs
Publication statusPublished - 2 Jan 1997
Externally publishedYes

Keywords

  • Learning systems
  • Neural networks
  • Signal processing

Fingerprint

Dive into the research topics of 'Sequential blind signal extraction in order specified by stochastic properties'. Together they form a unique fingerprint.

Cite this