An Improved Minimum Error Entropy Criterion with Self Adjusting Step-Size

In this paper, we propose minimum error entropy with self adjusting step-size (MEE-SAS) as an alternative to the minimum error entropy (MEE) algorithm for training adaptive systems. MEE-SAS has faster speed of convergence as compared to MEE technique for the same misadjustment. We attribute this characteristic to automatic learning rate inherent in MEE-SAS where the changing step size helps the algorithm to take large "jumps" when far away from the optimal solution and small "jumps" when near the solution. We test the performance of both the algorithms for two classic problems of system identification and prediction. However, we show that MEE performs better than MEE-SAS in situations where tracking ability of the optimal solution is required like in the case of non-stationary signals