Regularized numerical optimization of fuzzy rule bases

Autoren Johannes Himmelbauer
Mario Drobics
Titel Regularized numerical optimization of fuzzy rule bases
Buchtitel Proc. 13th IEEE Int. Conf. on Fuzzy Systems
Typ in Konferenzband
Verlag IEEE Press
Ort Budapest, Hungary
ISBN 0-7803-8354-0
Monat July
Jahr 2004
Seiten 1655 - 1660
SCCH ID# 405

This paper is devoted to the mathematical analysis and the numerical solution of data-driven optimization for an important class of fuzzy controllers, so-called Sugeno controllers. In contrast to other approaches which optimize the underlying fuzzy sets, we will mainly focus on the linear approximation of the output variable according to the input data. While the first approach leads to nonlinear problems, the latter will result in a free, linear least squares system to be solved. Therefore this approach can be used for high dimensional problems as well, when due to the increasing complexity nonlinear systems are no longer applicable.By applying Tikhonov regularization we get stable and fast algorithms that create sufficiently optimized controllers; with saving their interpretability. Finally we will show, how variable selection can be used to increase interpretability and to reduce computation time.