2020 IEEE Wireless Communications and Networking Conference (WCNC) 2020
DOI: 10.1109/wcnc45663.2020.9120517
|View full text |Cite
|
Sign up to set email alerts
|

Neural Network MIMO Detection for Coded Wireless Communication with Impairments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
16
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
1
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 14 publications
(17 citation statements)
references
References 26 publications
0
16
1
Order By: Relevance
“…If the system is based on MIMO-OFDM, then multiple subcarriers can be executed in parallel for increased efficiency. This follows the lines of prior work in deep learning-based detection schemes [23,25] and allows for compact models that can be efficiently executed using vector arithmetic units. Given the vector of received data streams y, the channel H and estimated noise variance 2 , the architecture uses them to operate in one of the following modes.…”
Section: 3mentioning
confidence: 95%
See 1 more Smart Citation
“…If the system is based on MIMO-OFDM, then multiple subcarriers can be executed in parallel for increased efficiency. This follows the lines of prior work in deep learning-based detection schemes [23,25] and allows for compact models that can be efficiently executed using vector arithmetic units. Given the vector of received data streams y, the channel H and estimated noise variance 2 , the architecture uses them to operate in one of the following modes.…”
Section: 3mentioning
confidence: 95%
“…This method has the advantage of a very small number of learnable parameters, but has a relatively large end-to-end latency because of the matrix operations involved during inference. The work in [25] takes a similar approach, but replaces the fixed computations of the OAMP algorithm with fully learnable transforms (i.e., layers of a deep neural network), resulting in competitive results for MIMO soft bit estimation and an architecture that can be scaled to high-dimensional scenarios. Finally, the work in [26] trains a two-layer deep neural network using a supervised loss directly on the soft bits, in single-input single-output (SISO) channels, leveraging that, in this case, a closed-form linear approximation of the soft bits exists.…”
Section: Soft Bit Estimationmentioning
confidence: 99%
“…In the case where the Rx has CSI knowledge (CSIR), several learning-based MIMO detectors have been proposed [9]- [13]. Specifically, the authors in [9] achieved excellent detection performance with a deep neural network architecture called DetNet, e.g., with a performance matching a semi-definite relaxation (SDR) baseline for independent and identically distributed (i.i.d.)…”
Section: Introductionmentioning
confidence: 99%
“…In the same context of online training and motivated by practical implementation, EPNet [12] was proposed to perform signal detection by unfolding the expectation propagation (EP) algorithm and training the damping factors. To support coded systems, a neural-network MIMO detector with impairments was proposed in [13], where the detection algorithm design is based upon projected gradient descent iterations for MIMO-OFDM systems. Empirical results show the robustness of the proposed detection scheme against several common communication impairments, since the NN does not assume any specific model.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation