An End-to-End Auto-Encoder Algorithm for Hardware-Impaired Transceivers Based on Meta and Joint Learning

The application of Deep learning (DL) in wireless communications has achieved remarkable success. However, there are still marked challenges impeding its use in the physical layer, largely due to the random nature of the wireless channel. This work investigates an end-to-end transceiver based on an unsupervised auto-encoder. We aim to detect a wireless signal suffering from transceiver hardware impairments as it passes through the fading channel. Furthermore, we examine the ability of this receiver to detect signals corrupted with non-Gaussian noise. We use meta and joint learning techniques to train the auto-encoder transceiver with random unknown channels and HWIs to simulate real channel conditions. We compare the results with maximum likelihood detection (MLD) in terms of bit error rate (BER). Our results demonstrate that using meta-learning to train the auto-encoder enhances system performance by reducing the BER of the received signal.