Investigation of the performance of multi-input multi-output detectors based on deep learning in non-Gaussian environments

<span lang="EN-US">The next generation of wireless cellular communication networks must be energy efficient, extremely reliable, and have low latency, leading to the necessity using algorithms based on deep neural (DNN) which better bit error rate (BER) or symbol (SER) performance than traditional complex multi-antenna multi-input multi-output (MIMO) detectors. This paper examines iterative detectors such as OAMP-Net information theory criteria maximum correntropy criterion (MCC) for implementation MIMO in non-Gaussian environments, results illustrate that proposed method has BER SER performance.</span>