Low-Complexity Data-Driven Communication Neural Receivers
Communication receivers based on deep learning have become a research hotspot in recent years. However, the excessive computational complexity and storage complexity prevent it from being deployed on communication hardware with limited resources. In order to reduce the computational complexity and r...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819393/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Communication receivers based on deep learning have become a research hotspot in recent years. However, the excessive computational complexity and storage complexity prevent it from being deployed on communication hardware with limited resources. In order to reduce the computational complexity and required storage resources of communication neural receivers based on deep learning, we propose to use candecomp parafac (CP), Tucker, tensor-train (TT) and tensor-ring (TR) decomposition respectively to compress the data-driven deep learning based communication neural receiver. Through compression, the storage resources required by the communication neural receiver are reduced by about half with bit error rate (BER) performance degradation of only 0.75dB to 1.3dB. |
|---|---|
| ISSN: | 2169-3536 |