Title :
Adaptive decision-feedback equalization of digital transmission channels using forward-only counterpropagation networks
Author :
Manabe, Takeshi ; Kaneda, Ryuji
Author_Institution :
ATR Opt. & Radio Commun. Res. Lab., Kyogo, Japan
Abstract :
An application of the forward-only counterpropagation network (FCPN) is proposed for nonlinear equalization of digital transmission channels. The learning mechanism of the FCPN is a combination of unsupervised self-organization and supervised training. A decision-feedback equalizer (DFE) based on FCPN was simulated on a digital computer. The results of the simulation demonstrate a superior bit-error rate performance of the FCPN-based DFE over the conventional DFE based on transversal filers, especially in high signal-to-noise-ratio conditions. It is also shown that the FCPN-based DFE can adaptively equalize time-varying transmission channels by using this self-organization mechanism
Keywords :
digital communication systems; equalisers; learning systems; neural nets; telecommunication channels; telecommunications computing; adaptive decision feedback equalisation; digital communication systems; digital transmission channels; forward-only counterpropagation networks; neural nets; nonlinear equalization; self-organization mechanism; supervised training; unsupervised self-organization; Adaptive equalizers; Computational modeling; Decision feedback equalizers; Digital communication; Laboratories; Learning systems; Multi-layer neural network; Multilayer perceptrons; Neural networks; Transversal filters;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170407
