Simple ML Detector for Multiple Antennas Communication System. In order to support providing broadbandwireless communication services against limited and expensive frequency bandwidth, we have to develop a bandwidthefficient system. Therefore, in this paper we propose a closed-loop MIMO (Multiple-Input-Multiple-Output) systemusing ML (Maximum Likelihood) detector to optimize capacity and to increase system performance. What is especiallyexciting about the benefits offered by MIMO is that a high capacity and performance can be attained without additionalfrequency-spectral resource. The grand scenario of this concept is the attained advantages of transformation matriceshaving capability to allocate transmitted signals power suit to the channel. Furthermore, product of these matrices formsparallel singular channels. Due to zero inter-channels correlation, thus we can design ML detector to increase thesystem performance. Finally, computer simulations validates that at 0 dB SNR our system can reach optimal capacityup to 1 bps/Hz and SER up to 0.2 higher than opened-loop MIMO.