New learning algorithm for blind separation of sources
- 8 October 1992
- journal article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 28 (21) , 1986-1987
- https://doi.org/10.1049/el:19921273
Abstract
A new improved, easily implementible learning algorithm for blind separation of statistically independent unknown source signals is proposed. In contrast to the well known algorithms, two time trajectories of synaptic weights {wij(t)}̃ and {Wij(t)} are computed where Wij(t) is the time average of wij(t)̃. Extensive computer simulation experiments have confirmed that the proposed learning algorithm assures a high convergence speed of the neural network for a blind identification problem, i.e. a quick recovering of unknown signals from the observation of a linear combination (mixture) of them. The algorithm can easily be extended to other applications.Keywords
This publication has 3 references indexed in Scilit:
- Adaptive optimization of neural algorithmsPublished by Springer Nature ,2006
- Neural networks for computing eigenvalues and eigenvectorsBiological Cybernetics, 1992
- CMOS Integration of Herault-Jutten Cells for Separation of SourcesPublished by Springer Nature ,1989