Share Email Print

Proceedings Paper

Hebbian- and anti-Hebbian-type neural network for blind separation of nonstationary signals
Author(s): Anke Meyer-Baese
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This contribution describes a neural network that self- organizes to recover the original signals from sensor signals. No particular information is required about the statistical properties of the sources and the coefficients of the linear-transformation, except the fact that the source signals are statistically independent and non- stationary. The learning rule for the network's parameters is derived from the steepest descent minimization of a time- dependent cost function that takes the minimum only when the network outputs are correlated with each other.

Paper Details

Date Published: 21 March 2001
PDF: 8 pages
Proc. SPIE 4390, Applications and Science of Computational Intelligence IV, (21 March 2001); doi: 10.1117/12.421166
Show Author Affiliations
Anke Meyer-Baese, Univ. of Florida (United States)

Published in SPIE Proceedings Vol. 4390:
Applications and Science of Computational Intelligence IV
Kevin L. Priddy; Paul E. Keller; Peter J. Angeline, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?