.png){kind=icon}
返回
Dynamic Neural Network for MIMO Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/JSAC.2022.3180794.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Achieving adequate precision in deep learning based communications often requires large network architectures, which results into unacceptable time delay and power consumption. This paper introduces the dynamic neural network (DyNN) into the design of wireless communications systems. DyNN allocates different samples with computation resources on demand by preforming dynamic inferences, thereby reducing the redundant computational cost and enhancing the network efficiency. We design a dynamic depth architecture that allows samples to adaptively skip layers with various dynamic strategies, from which we further develop a confidence criterion based dynamic improved DetNet (CD-IDetNet) and a policy network based dynamic improved DetNet (PD-IDetNet) for multiple-input multiple-output (MIMO) detection. Specifically, in CD-IDetNet, a confidence criterion is adopted to control samples exiting early, while in PD-IDetNet, policy networks are trained by reinforcement learning to selectively skip layers for varying samples. Simulation results demonstrate that CD-IDetNet and PD-IDetNet detectors can respectively reduce 17.4% and 31.1% computational costs while preserving the full accuracy of IDetNet. Desirable tradeoffs between accuracy and computational complexity can be further achieved by fine-tuning the hyper-parameters of CD-IDetNet and PD-IDetNet. Moreover, over-the-air (OTA) tests are conducted to validate the effectiveness of the proposed detectors in practical systems.
Keyword:
Computational modeling
MIMO communication
Detectors
Adaptation models
Wireless communication
Heuristic algorithms
Neural networks
MIMO detection
dynamic neural network
complexity reduction
deep learning
reinforcement learning
期刊
IF:
17.2
论文数:
6.4K
被引数:
3.1W
机构
引用论文
.png){kind=icon}
分享收藏Deep Transfer Learning-Based Downlink Channel Prediction for FDD Massive MIMO Systems基于深度转移学习的FDD大规模MIMO系统下行信道预测
OAAI
OAAI分享收藏Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System基于深度学习的FDD大规模MIMO系统下行信道预测OAAI
OAAI分享收藏Channel Estimation for mmWave Massive MIMO With Convolutional Blind Denoising Network基于卷积盲去噪网络的毫米波大规模MIMO信道估计
PREAI
分享收藏Haze Optical Properties from Long-Term Ground-Based Remote Sensing over Beijing and Xuzhou, ChinaOAAI
OAAI分享收藏
查看更多内容