This paper proposes a novel tensor-train deep neural network (TT-DNN) based channel estimator to tackle challenges of time-varying channel estimation in multiple-input multiple-output (MIMO) systems. A centralized DNN channel estimator can be realized by a distributed TT-DNN with parallel paths. The TT-DNN provides a compact representation by decomposing each DNN layer into a TT format with fewer model parameters, and is well-designed to adapt to the block structure, pilot density, and the number of MIMO antennas. Moreover, the channel estimation is performed in block-by-block and antenna-by-antenna manners such that both input dimensions of TT-DNN and the number of model parameters can be further reduced. In addition, a preliminary stage of model pre-training is set for the DNN/TT-DNN channel estimator which boosts the channel estimation accuracy. Moreover, the proposed TT-DNN is generalized to semiblind channel estimation scenarios where there exists only preamble training symbols. Our experiments show that the proposed TT-DNN based channel estimator outperforms the DNN counterparts in terms of convergence rate, estimation accuracy, and robustness, and presents better performance than recurrent neural network for semiblind channel estimation.

中文翻译：

---

设计用于时变MIMO信道估计的Tensor-train深层神经网络

本文提出了一种新颖的基于张量-深度神经网络（TT-DNN）的信道估计器，以应对多输入多输出（MIMO）系统中时变信道估计的挑战。集中式DNN信道估计器可以通过具有并行路径的分布式TT-DNN实现。TT-DNN通过将每个DNN层分解为具有较少模型参数的TT格式来提供紧凑的表示形式，并且经过精心设计以适应块结构，导频密度和MIMO天线的数量。此外，以逐块和逐天线的方式执行信道估计，从​​而可以进一步减少TT-DNN的输入尺寸和模型参数的数量。另外，为DNN / TT-DNN信道估计器设置了模型预训练的初步阶段，这提高了信道估计的准确性。此外，所提出的TT-DNN被推广到仅存在前导训练符号的半盲信道估计场景。我们的实验表明，基于TT-DNN的信道估计器在收敛速度，估计精度和鲁棒性方面均优于DNN，并且在半盲信道估计方面比循环神经网络具有更好的性能。