Achieving adequate precision in deep learning based communications often requires large network architectures, which results into unacceptable time delay and power consumption. This paper introduces the dynamic neural network (DyNN) into the design of wireless communications systems. DyNN allocates different samples with computation resources on demand by preforming dynamic inferences, thereby reducing the redundant computational cost and enhancing the network efficiency. We design a dynamic depth architecture that allows samples to adaptively skip layers with various dynamic strategies, from which we further develop a confidence criterion based dynamic improved DetNet (CD-IDetNet) and a policy network based dynamic improved DetNet (PD-IDetNet) for multiple-input multiple-output (MIMO) detection. Specifically, in CD-IDetNet, a confidence criterion is adopted to control samples exiting early, while in PD-IDetNet, policy networks are trained by reinforcement learning to selectively skip layers for varying samples. Simulation results demonstrate that CD-IDetNet and PD-IDetNet detectors can respectively reduce 17.4% and 31.1% computational costs while preserving the full accuracy of IDetNet. Desirable tradeoffs between accuracy and computational complexity can be further achieved by fine-tuning the hyper-parameters of CD-IDetNet and PD-IDetNet. Moreover, over-the-air (OTA) tests are conducted to validate the effectiveness of the proposed detectors in practical systems.

中文翻译：

---

用于 MIMO 检测的动态神经网络

在基于深度学习的通信中实现足够的精度通常需要大型网络架构，这会导致不可接受的时间延迟和功耗。本文将动态神经网络（DyNN）引入到无线通信系统的设计中。DyNN通过进行动态推理，根据需要为不同的样本分配计算资源，从而减少冗余计算成本，提高网络效率。我们设计了一个动态深度架构，允许样本自适应地跳过具有各种动态策略的层，从中我们进一步开发了一个基于信心标准的动态改进DetNet (CD-IDetNet) 和一个基于策略网络的d动态改进DetNet (PD-IDetNet) 用于多输入多输出 (MIMO) 检测。具体来说，在 CD-IDetNet 中，采用置信度标准来控制样本提前退出，而在 PD-IDetNet 中，策略网络通过强化学习进行训练，以选择性地跳过不同样本的层。仿真结果表明，CD-IDetNet 和 PD-IDetNet 检测器可以分别降低 17.4% 和 31.1% 的计算成本，同时保持 IDetNet 的完整精度。通过微调 CD-IDetNet 和 PD-IDetNet 的超参数，可以进一步实现准确度和计算复杂度之间的理想权衡。此外，进行空中（OTA）测试以验证所提出的探测器在实际系统中的有效性。