Autoencoder-based MIMO Communications with Learnable ADCs.

With the growing demand for high-speed data transmission, multiple-input multiple-output (MIMO) technology has been widely used in 5G wireless communication systems. Practically, analog-to-digital converters (ADCs) are employed to reduce the high power consumption problem caused by using a large number of antennas. However, one significant bottleneck restricting the performance of such MIMO systems is the infeasibility to jointly design the transceiver and the ADCs. To address this problem, this paper proposes an autoencoder solution driven by deep learning methods, for MIMO Rayleigh fading channels. Specifically, by viewing the entire MIMO system as an auto encoder, the encoding-decoding pair and the ADCs can be trained simultaneously and optimized in an end-to-end manner, which can also be easily adapted for different information transmission rates. Moreover, in order to enable the gradient passing for ADCs, a smooth function (i.e., arctan(.)) is used to finely approximate the quantization layers of original ADCs. Finally, simulation results reveal the improved performance on both accuracy and stability of the proposed autoencoder based framework in MIMO systems.