Stability analysis of learning algorithms for blind source separation

Shun Ichi Amari, Tian Ping Chen, Andrzej Cichocki

Research output: Contribution to journalArticlepeer-review

240 Citations (SciVal)


Recently a number of adaptive learning algorithms have been proposed for blind source separation. Although the underlying principles and approaches are different, most of them have very similar forms. Two important issues remained to be elucidated further: the statistical efficiency and the stability of learning algorithms. The present letter analyzes a general form of statistically efficient algorithms and gives a necessary and sufficient condition for the separating solution to be a stable equilibrium of a general learning algorithm. Moreover, when the separating solution is unstable, a simple method is given for stabilizing the separating solution by modifying the algorithm.

Original languageEnglish
Pages (from-to)1345-1351
Number of pages7
JournalNeural Networks
Issue number8
Publication statusPublished - Nov 1997
Externally publishedYes


  • Blind source separation
  • Efficiency of learning
  • Independent component analysis (ICA)
  • Natural gradient
  • Stability of learning


Dive into the research topics of 'Stability analysis of learning algorithms for blind source separation'. Together they form a unique fingerprint.

Cite this