Physical layer deep learning of encodings for the MIMO fading channel

We introduce a novel physical layer scheme for Multiple Input Multiple Output (MIMO) communications based on unsupervised deep learning using an autoencoder. This method extends prior work on the joint optimization of physical layer representation and encoding and decoding processes as a single end-to-end task by expanding the transmitter and receiver to the multi-antenna case. We introduce a domain appropriate wireless channel impairment model (the multi-input multi-output Rayleigh fading channel), into the autoencoder optimization problem in order to directly learn a system which optimizes for it. This approach demonstrates significant potential for learning schemes which achieve and exceed performance of current day methods which are widely used in existing wireless MIMO systems. We discuss how the scheme can be easily adapted for open-loop and closed-loop operation in spatial multiplexing modes as well as spatial diversity modes. Each of these modes is learned and realized using the same simple and compact approach.