Learning to Detect

By Neev Samuel, Tzvi Diskin, Ami Wiesel. IEEE Transactions on Signal Processing, 2018

494 citations recorded by the source corpus.

In this paper, we consider multiple-input-multiple-output detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a detection network (DetNet), which is specifically designed for the task. The structure of DetNet is obtained by unfolding the iterations of a projected gradient descent algorithm into a network. We compare the accuracy and runtime complexity of the proposed approaches and achieve state-of-the-art performance while maintaining low computational requirements. Furthermore, we manage to train a single network to detect over an entire distribution of channels. Finally, we consider detection with soft outputs and show that the networks can easily be modified to produce soft decisions.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/a1734c15bd7dd00aa032537634f7d4a985f09c62

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Geoffrey Y. Li
2. Merouane Debbah
3. Shi Jin
4. Chao-Kai Wen
5. M. Di Renzo
6. Alessio Zappone
7. Hengtao He
8. F. Gao

Citations in the corpus

• Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, methodology): “Deep learning is used for data detection in MIMO systems in [163], [164], in decodeand-forward relay channels [165], and for equalization and synchronization in OFDM systems in [166].”
• Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach (2021, unknown): “…various design problems of data-oriented communication , including transceiver structures [7], source/channel coding [8], signal detection [9], and radio resource management [10], have been revisited intensively using AI techniques, especially deep neural networks (DNNs), breeding the…”
• Deep MIMO detection (2017, background): “For more details, see [24], where further information is presented.”
• Model-Driven Deep Learning for Physical Layer Communications (2018, methodology): “To address the above issues, a model-driven DL approach, called detection network (DetNet), has been designed in [15] by applying a projected gradient descent method for detecting maximum likelihood in a neural network.”
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, background): “A lot of research has attempted to use DL to address physical layer issues, including channel decoding [17, 18], detection [19–21], channel estimation [22–24], and resource management [25–32].”
• Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, methodology): “Furthermore, DNN based architectures for symbol detection in MIMO systems have been proposed in [98], and a DNN-based localization method exploiting fingerprint-based and channel measurements for M-MIMO systems has been proposed in [99].”