The aim of this work is to present a generalized Hebbian learning theory fo
r complex-weighted linear feed-forward network endowed with lateral inhibit
ory connections, and to show how it can be applied to blind separation from
complex-valued mixtures. We start by stating an optimization principle for
Kung-Diamantaras' network which leads to a generalized APEX-like learning
theory relying on some non-linear functions, whose choice determines networ
k's ability. Then we recall the Sudjianto-Hassoun interpretation of Hebbian
learning and show that it drives us to the choice of the right set of non-
linear functions allowing the network to achieve blind separation. The prop
osed approach is finally assessed by numerical simulations. (C) 2000 Publis
hed by Elsevier Science B.V. All rights reserved.