A hierarchical feedforward adaptive filter for system identification
Tóm tắt
An architecture for adaptive filtering based upon the previously introduced hierarchical least mean square algorithm is proposed. This pyramidal architecture incorporates sparse connections between the architectural layers with a certain variable degree of overlapping between the neighboring subfilters of the same level. A learning algorithm for this class of structures is derived, based on the back-propagation algorithm for temporal feedforward networks with linear neurons. Further, a class of normalized algorithms for this class is derived. The analysis and simulations show the proposed algorithms outperform the existing ones.
Từ khóa
#Adaptive filters #System identification #Signal processing algorithms #Neurons #Finite impulse response filter #Neural networks #Adaptive signal processing #Biomedical signal processing #Least squares approximation #Feedforward neural networksTài liệu tham khảo
haykin, 1994, Neural Networks, A Comprehensive Foundation
10.1109/NNSP.2001.943111
10.1109/97.969448
mandie, 2001, Recurrent Neural Networks for Predfction, Learning algorithm Architecture and stability
10.1109/97.969446
10.1109/78.709548
farhang-boroujeny, 1998, Adaptive Filters: Theory and Applications
boukis, 2002, On the Choice of Parameters and Performance of the Hierarchical Least Mean Square Algorithm, IEEE Signal Processing Letters