Using a nonlinear 15-state helicopter model in 6 DOF, two di erent neural control systems, both acting as rate damping, have been designed and compared. They are both based on the ...
Abstract. In this paper, we presen t an algorithm that provides adaptive plasticity in function approximation problems: the deformable (feature) map (DM) algorithm. The DM approach...
We derive continuous-time batch and online versions of the recently introduced efficient O(N2 ) training algorithm of Atiya and Parlos [2000] for fully recurrent networks. A mathem...
In this paper we shortly discuss the K.U. Leuven time-series prediction competition, which has been held in the framework of the International Workshop on Advanced Black-Box Techni...
It has been shown that self-organized maps, when adequately trained with the set of integers 1 to 32, lay out real numbers in a 2D map in an ordering that is superior to any of the...