Details

Autor(en) / Beteiligte

• Samuel, Neev
• Diskin, Tzvi
• Wiesel, Ami

Titel

Learning to Detect

Ist Teil von

• IEEE transactions on signal processing, 2019-05, Vol.67 (10), p.2554-2564

Ort / Verlag

New York: IEEE

Erscheinungsjahr

2019

Quelle

IEL

Beschreibungen/Notizen

• 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.