Model-Driven Deep Learning for MIMO Detection

In this talk, we investigate the model-driven deep learning for multiple input-multiple output (MIMO) detection. In particular, the MIMO detector is specially designed by unfolding an iterative algorithm and adding some trainable parameters. because the number of trainable parameters is much fewer than the data-driven deep-learning-based signal detector, the model-driven deep-learning-based MIMO detector can be rapidly trained with a much smaller data set. The proposed MIMO detector can be extended to soft input-soft output detection easily. Furthermore, we investigate joint MIMO channel estimation and signal detection, where the detector takes channel estimation error and channel statistics into consideration, while channel estimation is refined by detected data and considers the detection error. Based on numerical results, the model-driven deep-learning-based MIMO detector significantly improves the performance of corresponding traditional iterative detectors, outperforms other deep-learning-based MIMO detectors and exhibits superior robustness to various mismatches.