Complexity-Scalable Neural-Network-Based MIMO Detection With Learnable Weight Scaling
- 7 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (10) , 6101-6113
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 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.Keywords
All Related Versions
Funding Information
- EPSRC (EP/S028455/1, EP/R035342/1)
- Petroleum Technology Development Fund (PTDF) Overseas Scholarship Scheme, Nigeria (PTDF/ED/PHD/MA/1003/16)
- IEEE International Conference on Communications ICC 2020, Dublin, Ireland
This publication has 35 references indexed in Scilit:
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Global Optimality in Neural Network Training2017
- Group sparse regularization for deep neural networksNeurocomputing, 2017
- On deep learning-based channel decoding2017
- Learning to decode linear codes using deep learning2017
- Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention2016
- 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
- Semidefinite relaxation based multiuser detection for M-ary PSK multiuser systemsIEEE Transactions on Signal Processing, 2004
- An artificial neural net Viterbi decoderIEEE Transactions on Communications, 1996