Title :
Comparison of a neural network based receiver to the optimal and multistage CDMA multiuser detectors
Author :
Kechriotis, George I. ; Manolakos, Elias S.
Author_Institution :
Thinking Machines Corp., Cambridge, MA, USA
fDate :
31 Aug-2 Sep 1995
Abstract :
We compare the Hopfield neural network (HNN) based CDMA multiuser detection to the optimal multiuser detector (OMD) and the suboptimal multistage detector (MSD). It is shown that the HNN receiver is a powerful generalization of the MSD. Moreover, it is shown that by fine tuning the parameters of the HNN it is possible to achieve BER performance that exceeds that of the MSD and gets very close to the optimal
Keywords :
Hopfield neural nets; code division multiple access; radio receivers; signal detection; spread spectrum communication; telecommunication computing; Hopfield neural network; multistage CDMA multiuser detectors; neural network based receiver; optimal multiuser detector; parameter fine tuning; suboptimal multistage detector; Bit error rate; Detectors; Digital signal processing; Gaussian channels; Hopfield neural networks; Multiaccess communication; Multiuser detection; Neural networks; Recurrent neural networks; Transmitters;
Conference_Titel :
Neural Networks for Signal Processing [1995] V. Proceedings of the 1995 IEEE Workshop
Conference_Location :
Cambridge, MA
Print_ISBN :
0-7803-2739-X
DOI :
10.1109/NNSP.1995.514936
