A signal suffers from nonlinear, linear, and additive distortion when trans
mitted through a channel. Linear equalizers are commonly used in receivers
to compensate for linear channel distortion. As an alternative, novel equal
izer structures utilizing neural computation have been developed for compen
sating for nonlinear channel distortion. In this paper, we propose a neural
detector based on self-organizing map (SOM) in a 16 QAM system. The propos
ed scheme uses the SOM algorithm and symbol-by-symbol detector to form a ne
ural detector, and it adapts well to the changing channel conditions, inclu
ding nonlinear distortions because of the topology-preserving property of t
he SOM algorithm. According to the theoretical analysis and computer simula
tion results, the proposed scheme is shown to have better performance than
traditional linear equalizer when facing with nonlinear distortion.