TY - GEN
T1 - Neural network-based decision feedback equalizer using a recursive least squares algorithm
AU - Mahmood, Kashif
AU - Zerguine, Azzedine
PY - 2005
Y1 - 2005
N2 - In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used for a decision feedback equalization (DFE) scenario. Its performance is investigated and compared to those of MLP-DFE based on the back propagation (BP) algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying fading channels.
AB - In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used for a decision feedback equalization (DFE) scenario. Its performance is investigated and compared to those of MLP-DFE based on the back propagation (BP) algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying fading channels.
UR - https://www.scopus.com/pages/publications/33847136130
U2 - 10.1109/ISSPA.2005.1580201
DO - 10.1109/ISSPA.2005.1580201
M3 - Conference contribution
AN - SCOPUS:33847136130
SN - 0780392434
SN - 9780780392434
T3 - Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005
SP - 82
EP - 85
BT - Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005
ER -