Complexity-Scalable Neural Network Based MIMO Detection With Learnable Weight Scaling
Preprint
Abstract
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 scalable complexity-accuracy results. To reduce complexity further, we introduce a regularization constraint on the layer weights such that, at inference, parts (or the entirety) of network layers can be removed with minimal impact on the detection accuracy. We also introduce trainable weight-scaling functions for increased robustness to changes in the activation patterns and a further improvement in the detection accuracy at the same inference complexity. Numerical results show that our approach is 10 and 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Multilevel MIMO Detection with Deep Learning2018
- Deep learning for wireless physical layer: Opportunities and challengesChina Communications, 2017
- Deep Learning Based Communication Over the AirIEEE Journal of Selected Topics in Signal Processing, 2017
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- Next Generation 5G Wireless Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2016
- An Overview of Massive MIMO: Benefits and ChallengesIEEE Journal of Selected Topics in Signal Processing, 2014
- Cellular architecture and key technologies for 5G wireless communication networksIEEE Communications Magazine, 2014
- Semidefinite Relaxation of Quadratic Optimization ProblemsIEEE Signal Processing Magazine, 2010
- A Semidefinite Relaxation Approach to MIMO Detection for High-Order QAM ConstellationsIEEE Signal Processing Letters, 2006
- Semidefinite relaxation for detection of 16-QAM signaling in MIMO channelsIEEE Signal Processing Letters, 2005