.png){kind=icon}
返回
Complexity-Scalable Neural-Network-Based MIMO Detection With Learnable Weight Scaling
.png){kind=icon}
OA
AI
DOI：10.1109/TCOMM.2020.3007622.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper introduces a framework for systematic complexity scaling of deep neural network (DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-fold and 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.
Keyword:
Complexity theory
Detectors
MIMO communication
Computational modeling
Training
Computer architecture
Neural networks
MIMO detection
deep neural networks
DetNet
profile weight coefficients
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.3
论文数:
1.2W
被引数:
3.6W
机构
引用论文
.png){kind=icon}
查看更多内容