Title :
Mean-square error surfaces of 2-D recursive adaptive filters
Author :
Strait, Jeffrey C. ; Jenkins, W. Kenneth
Author_Institution :
Coordinated Sci. Lab., Illinois Univ., Urbana, IL, USA
Abstract :
Recursive adaptive filters which utilize a stochastic gradient search algorithm in order to optimize their coefficients are apt to converge to local minima if the mean-square error surface is not unimodal. Such conditions are known to result since the IIR mean-square error surfaces is not quadratic. Two-dimensional adaptive filter error surfaces are examined in this paper, and their properties are seen to be very similar to those of 1-D IIR adaptive filter error surfaces
Keywords :
adaptive filters; approximation theory; error analysis; filtering theory; identification; recursive filters; two-dimensional digital filters; 2D adaptive filter error surfaces; 2D recursive adaptive filters; mean-square error surfaces; stochastic gradient search algorithm; two-dimensional adaptive filter; Adaptive filters; Computer errors; Finite impulse response filter; IIR filters; Image processing; Pulse modulation; Signal processing algorithms; Stochastic processes; System identification; Video signal processing;
Conference_Titel :
Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on
Conference_Location :
Lafayette, LA
Print_ISBN :
0-7803-2428-5
DOI :
10.1109/MWSCAS.1994.518935
