A novel feed-forward neural network blind multi-user detection algorithm by augmented Lagrange optimization

A feed-forward neural network blind multi-user detection algorithm was proposed. Feed-forward neural network and constant modulus algorithm (CMA) were consociated to complete blind multi-user detection. A constant modulus cost function firstly was constructed and the cost function with restrict condition was optimized by augmented Lagrange method. Blind multi-user detection algorithm was realized by iterative equations of FNN. And computer simulation indicates the new algorithm improves the ability to overcome MAI and makes bit error ratio lower.