Learning algorithms for blind multiuser detection in CDMA downlink

CDMA (code division multiple access) is a multiple access technique based on spread spectrum methods. In a downlink signal processing, only the code of the mobile phone user is known, while the codes of the interfering users are unknown. Blind source separation or multiuser detection is an approach offering the solution to this problem. In this work, we compare novel and efficient learning blind source separation algorithms for estimating the symbols in AWGN channel. Simulations show that one can estimate the symbols without any knowledge of the chip sequences.