Richard Saeks

Learn More
An Adaptive Dynamic Programming algorithm for nonlinear systems with unknown dynamics is developed. The algorithm is initialized with a positive definite cost functional / stabilizing control law pair (V 0 , k 0) (coupled via the Hamilton Jacobi Bellman Equation). Given (V i , k i), one runs the system using control law k i recording the state and control(More)
It is shown that a Hopfield neural network (with linear transfer functions) augmented by an additional feedforward layer can be used to compute the Moore-Penrose generalized inverse of a matrix. The resultant augmented linear Hopfield network can be used to solve an arbitrary set of linear equations or, alternatively, to solve a constrained least squares(More)
  • 1