Title :
Nonlinear Adaptive Equalizer Using a Pipelined Decision Feedback Recurrent Neural Network in Communication Systems
Author :
Zhao, Haiquan ; Zeng, Xiangping ; Zhang, Jiashu ; Li, Tianrui
Author_Institution :
Si-Chuan Province Key Lab. of Signal, Southwest Jiaotong Univ., Chengdu, China
fDate :
8/1/2010 12:00:00 AM
Abstract :
In this letter, a novel pipelined decision feedback RNN equalizer (PDFRNE) with low computational complexity is proposed. Since each module is a DFRNN with the decision feedback structure so that it can eliminate the past error remaining in the network. Moreover, the performance can be further improved. At the same time, it can overcome the unstableness due to its nature of the infinite impulse response (IIR) structure.
Keywords :
IIR filters; adaptive equalisers; decision feedback equalisers; pipeline processing; recurrent neural nets; communication systems; computational complexity; infinite impulse response structure; nonlinear adaptive equalizer; pipelined decision feedback recurrent neural network equalizer; Artificial neural networks; Computer architecture; Convergence; Equalizers; Neurons; Recurrent neural networks; Training; Adaptive equalizer; decision feedback recurrent neural network; pipelined architecture; recurrent neural network;
Journal_Title :
Communications, IEEE Transactions on
DOI :
10.1109/TCOMM.2010.08.080612
