Abstract: Rcently, the demand for ultra- reliable low latency communication for the 5G communication system has attracted extensive attention and research effort. However, the conventional communication systems are still limited to the tradtional communication theories, and lack hugh breakthrough in the network performance. As a promising machine learning tool to handle the accurate pattern recognition from complex raw data, deep learning (DL) is becoming a powerful method to handle communication problems, add intelligence to wireless networks with large-scale topology and complex
radio conditions. This paper mainly introduces the physical layer application based on deep learning, and proposes a deep Q-network (DQN) based MIMO system location information verification scheme to improve the accuracy of signal detection in a varing and unknown channel environment.

Key words: deep learning, signal detection, MIMO