A Dynamic Parzen Window Approach Based on Error-entropy Minimization Algorithm for Supervised Training of Nonlinear Adaptive System

This paper presents a dynamic Parzen window estimator in the MEE approach for supervised training of nonlinear adaptive system. By adjusting the Parzen window width dynamically so that the overall information force (OIF) among error-samples of each step is as large as possible, the training speed is accelerated and the error is reduced. The simulation result has proved the effectiveness and robustness of this algorithm.