Abstract— The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as find...
Emad A. El-Sebakhy, Salahadin Mohammed, Moustafa E...
Heuristics used by search algorithms are usually composed of more primitive functions which we call "features". A method for combining features is presented which is bas...
A learning problem might have several measures of complexity (e.g., norm and dimensionality) that affect the generalization error. What is the interaction between these complexiti...
In this paper we prove that a switched nonlinear system has several useful ISS-type properties under average dwell-time switching signals if each constituent dynamical system is I...
In this paper, a moving mesh discontinuous Galerkin (DG) method is developed to solve the nonlinear conservation laws. In the mesh adaptation part, two issues have received much a...