Self-adaptive neural networks for blind separation of sources

Andrzej Cichocki, Shun ichi Amari, Masaharu Adachi, Wlodzimierz Kasprzak

Research output: Contribution to journalConference articlepeer-review

35 Citations (Scopus)

Abstract

Novel on-line learning algorithms with self adaptive learning rates (parameters) for blind separation of signals are proposed. The main motivation for development of new learning rules is to improve convergence speed and to reduce cross-talking, especially for non-stationary signals. Furthermore, we have discovered that under some conditions the proposed neural network models with associated learning algorithms exhibit a random switch of attention, i.e. they have ability of chaotic or random switching or cross-over of output signals in such way that a specified separated signal may appear at various outputs at different time windows. Validity, performance and dynamic properties of the proposed learning algorithms are investigated by computer simulation experiments.

Original languageEnglish
Pages (from-to)157-160
Number of pages4
JournalProceedings - IEEE International Symposium on Circuits and Systems
Volume2
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 IEEE International Symposium on Circuits and Systems, ISCAS. Part 1 (of 4) - Atlanta, GA, USA
Duration: 12 May 199615 May 1996

Fingerprint

Dive into the research topics of 'Self-adaptive neural networks for blind separation of sources'. Together they form a unique fingerprint.

Cite this