This paper provides an approach for output feedback robust approximate pole
assignment. It is formulated as an unconstrained optimization problem and
solved via the gradient flow approach which is ideally suited for neural co
mputing implementation. A schematic circuit architecture of the neural netw
ork is suggested. Simulation results are used to demonstrate the effectiven
ess of the proposed method. (C) 1999 Elsevier Science B.V. All rights reser
ved.