我们根据光学通信中的载体回收率的变异推断研究了自适应盲人均衡器的潜力。这些均衡器基于最大似然通道估计的低复杂性近似。我们将变异自动编码器（VAE）均衡器的概念概括为包括概率星座塑形（PCS）的高阶调制格式，无处不在，在光学通信中，对接收器进行过度采样和双极化传输。除了基于卷积神经网络的黑盒均衡器外，我们还提出了基于线性蝴蝶滤波器的基于模型的均衡器，并使用变异推理范式训练过滤器系数。作为副产品，VAE还提供了可靠的通道估计。我们在具有符号间干扰（ISI）的经典添加剂白色高斯噪声（AWGN）通道和色散线性光学双极化通道上分析了VAE的性能和灵活性。我们表明，对于固定的固定通道但也随时间变化的通道，它可以超越最先进的恒定算法（CMA）来扩展盲人自适应均衡器的应用范围。评估伴随着超参数分析。

由于自动驾驶，物联网和流媒体服务的快速发展，现代通信系统必须应对各种渠道条件以及用户和设备的稳步增加。这以及仍在上升的带宽需求只能通过智能网络自动化来满足，这需要高度灵活和盲目的收发器算法。为了应对这些挑战，我们提出了一种新颖的自适应均衡计划，该计划通过训练用对抗性网络训练均衡器来利用深度学习的繁荣进步。该学习仅基于发射信号的统计数据，因此它对通道模型的实际发送符号和不可知论是盲目的。所提出的方法独立于均衡器拓扑，并实现了强大的基于神经网络的均衡器的应用。在这项工作中，我们证明了这一概念在对线性和非线性传输通道的模拟中，并证明了拟议的盲目学习方案的能力，可以接近非盲均衡器的性能。此外，我们提供了理论观点，并强调了方法的挑战。

在本文中，提出了一种新的方法，该方法允许基于神经网络（NN）均衡器的低复杂性发展，以缓解高速相干光学传输系统中的损伤。在这项工作中，我们提供了已应用于馈电和经常性NN设计的各种深层模型压缩方法的全面描述和比较。此外，我们评估了这些策略对每个NN均衡器的性能的影响。考虑量化，重量聚类，修剪和其他用于模型压缩的尖端策略。在这项工作中，我们提出并评估贝叶斯优化辅助压缩，其中选择了压缩的超参数以同时降低复杂性并提高性能。总之，通过使用模拟和实验数据来评估每种压缩方法的复杂性及其性能之间的权衡，以完成分析。通过利用最佳压缩方法，我们表明可以设计基于NN的均衡器，该均衡器比传统的数字背部传播（DBP）均衡器具有更好的性能，并且只有一个步骤。这是通过减少使用加权聚类和修剪算法后在NN均衡器中使用的乘数数量来完成的。此外，我们证明了基于NN的均衡器也可以实现卓越的性能，同时仍然保持与完整的电子色色散补偿块相同的复杂性。我们通过强调开放问题和现有挑战以及未来的研究方向来结束分析。

我们考虑在线性符号间干扰通道上使用因子图框架的符号检测的应用。基于Ungerboeck观察模型，可以得出具有吸引人复杂性能的检测算法。但是，由于基础因子图包含循环，因此总和算法（SPA）产生了次优算法。在本文中，我们制定并评估有效的策略，以通过神经增强来提高基于因子图的符号检测的性能。特别是，我们将因子节点的神经信念传播和概括是减轻因子图内周期效应的有效方法。通过将通用预处理器应用于通道输出，我们提出了一种简单的技术来改变每个SPA迭代中的基本因子图。使用这种动态因子图跃迁，我们打算保留水疗消息的外在性质，否则由于周期而受到损害。仿真结果表明，所提出的方法可以大大改善检测性能，甚至可以在各种传输方案中接近最大后验性能，同时保留在块长度和通道内存中线性线性的复杂性。

最近的作品表明，现代机器学习技术可以为长期存在的联合源通道编码（JSCC）问题提供另一种方法。非常有希望的初始结果，优于使用单独的源代码和通道代码的流行数字方案，已被证明用于使用深神经网络（DNNS）的无线图像和视频传输。但是，此类方案的端到端培训需要可区分的通道输入表示。因此，先前的工作假设可以通过通道传输任何复杂值。这可以防止在硬件或协议只能接收数字星座规定的某些频道输入集的情况下应用这些代码。本文中，我们建议使用有限通道输入字母的端到端优化的JSCC解决方案DeepJSCC-Q。我们表明，DEEPJSCC-Q可以实现与允许任何复杂的有价值通道输入的先前作品相似的性能，尤其是在可用的高调制订单时，并且在调制顺序增加的情况下，性能渐近接近无约束通道输入的情况。重要的是，DEEPJSCC-Q保留了不可预测的渠道条件下图像质量的优雅降级，这是在频道迅速变化的移动系统中部署的理想属性。

Channel estimation is a critical task in multiple-input multiple-output (MIMO) digital communications that substantially effects end-to-end system performance. In this work, we introduce a novel approach for channel estimation using deep score-based generative models. A model is trained to estimate the gradient of the logarithm of a distribution and is used to iteratively refine estimates given measurements of a signal. We introduce a framework for training score-based generative models for wireless MIMO channels and performing channel estimation based on posterior sampling at test time. We derive theoretical robustness guarantees for channel estimation with posterior sampling in single-input single-output scenarios, and experimentally verify performance in the MIMO setting. Our results in simulated channels show competitive in-distribution performance, and robust out-of-distribution performance, with gains of up to $5$ dB in end-to-end coded communication performance compared to supervised deep learning methods. Simulations on the number of pilots show that high fidelity channel estimation with $25$% pilot density is possible for MIMO channel sizes of up to $64 \times 256$. Complexity analysis reveals that model size can efficiently trade performance for estimation latency, and that the proposed approach is competitive with compressed sensing in terms of floating-point operation (FLOP) count.

Two of the main principles underlying the life cycle of an artificial intelligence (AI) module in communication networks are adaptation and monitoring. Adaptation refers to the need to adjust the operation of an AI module depending on the current conditions; while monitoring requires measures of the reliability of an AI module's decisions. Classical frequentist learning methods for the design of AI modules fall short on both counts of adaptation and monitoring, catering to one-off training and providing overconfident decisions. This paper proposes a solution to address both challenges by integrating meta-learning with Bayesian learning. As a specific use case, the problems of demodulation and equalization over a fading channel based on the availability of few pilots are studied. Meta-learning processes pilot information from multiple frames in order to extract useful shared properties of effective demodulators across frames. The resulting trained demodulators are demonstrated, via experiments, to offer better calibrated soft decisions, at the computational cost of running an ensemble of networks at run time. The capacity to quantify uncertainty in the model parameter space is further leveraged by extending Bayesian meta-learning to an active setting. In it, the designer can select in a sequential fashion channel conditions under which to generate data for meta-learning from a channel simulator. Bayesian active meta-learning is seen in experiments to significantly reduce the number of frames required to obtain efficient adaptation procedure for new frames.

Most semantic communication systems leverage deep learning models to provide end-to-end transmission performance surpassing the established source and channel coding approaches. While, so far, research has mainly focused on architecture and model improvements, but such a model trained over a full dataset and ergodic channel responses is unlikely to be optimal for every test instance. Due to limitations on the model capacity and imperfect optimization and generalization, such learned models will be suboptimal especially when the testing data distribution or channel response is different from that in the training phase, as is likely to be the case in practice. To tackle this, in this paper, we propose a novel semantic communication paradigm by leveraging the deep learning model's overfitting property. Our model can for instance be updated after deployment, which can further lead to substantial gains in terms of the transmission rate-distortion (RD) performance. This new system is named adaptive semantic communication (ASC). In our ASC system, the ingredients of wireless transmitted stream include both the semantic representations of source data and the adapted decoder model parameters. Specifically, we take the overfitting concept to the extreme, proposing a series of ingenious methods to adapt the semantic codec or representations to an individual data or channel state instance. The whole ASC system design is formulated as an optimization problem whose goal is to minimize the loss function that is a tripartite tradeoff among the data rate, model rate, and distortion terms. The experiments (including user study) verify the effectiveness and efficiency of our ASC system. Notably, the substantial gain of our overfitted coding paradigm can catalyze semantic communication upgrading to a new era.

在本文中，我们提出了一类新的高效的深源通道编码方法，可以在非线性变换下的源分布下，可以在名称非线性变换源通道编码（NTSCC）下收集。在所考虑的模型中，发射器首先了解非线性分析变换以将源数据映射到潜伏空间中，然后通过深关节源通道编码将潜在的表示发送到接收器。我们的模型在有效提取源语义特征并提供源通道编码的侧面信息之前，我们的模型包括强度。与现有的传统深度联合源通道编码方法不同，所提出的NTSCC基本上学习源潜像和熵模型，作为先前的潜在表示。因此，开发了新的自适应速率传输和高辅助辅助编解码器改进机制以升级深关节源通道编码。整个系统设计被制定为优化问题，其目标是最小化建立感知质量指标下的端到端传输率失真性能。在简单的示例源和测试图像源上，我们发现所提出的NTSCC传输方法通常优于使用标准的深关节源通道编码和基于经典分离的数字传输的模拟传输。值得注意的是，由于其剧烈的内容感知能力，所提出的NTSCC方法可能会支持未来的语义通信。

Ultra-reliable short-packet communication is a major challenge in future wireless networks with critical applications. To achieve ultra-reliable communications beyond 99.999%, this paper envisions a new interaction-based communication paradigm that exploits feedback from the receiver. We present AttentionCode, a new class of feedback codes leveraging deep learning (DL) technologies. The underpinnings of AttentionCode are three architectural innovations: AttentionNet, input restructuring, and adaptation to fading channels, accompanied by several training methods, including large-batch training, distributed learning, look-ahead optimizer, training-test signal-to-noise ratio (SNR) mismatch, and curriculum learning. The training methods can potentially be generalized to other wireless communication applications with machine learning. Numerical experiments verify that AttentionCode establishes a new state of the art among all DL-based feedback codes in both additive white Gaussian noise (AWGN) channels and fading channels. In AWGN channels with noiseless feedback, for example, AttentionCode achieves a block error rate (BLER) of $10^{-7}$ when the forward channel SNR is 0 dB for a block size of 50 bits, demonstrating the potential of AttentionCode to provide ultra-reliable short-packet communications.

Effective and adaptive interference management is required in next generation wireless communication systems. To address this challenge, Rate-Splitting Multiple Access (RSMA), relying on multi-antenna rate-splitting (RS) at the transmitter and successive interference cancellation (SIC) at the receivers, has been intensively studied in recent years, albeit mostly under the assumption of perfect Channel State Information at the Receiver (CSIR) and ideal capacity-achieving modulation and coding schemes. To assess its practical performance, benefits, and limits under more realistic conditions, this work proposes a novel design for a practical RSMA receiver based on model-based deep learning (MBDL) methods, which aims to unite the simple structure of the conventional SIC receiver and the robustness and model agnosticism of deep learning techniques. The MBDL receiver is evaluated in terms of uncoded Symbol Error Rate (SER), throughput performance through Link-Level Simulations (LLS), and average training overhead. Also, a comparison with the SIC receiver, with perfect and imperfect CSIR, is given. Results reveal that the MBDL receiver outperforms by a significant margin the SIC receiver with imperfect CSIR, due to its ability to generate on demand non-linear symbol detection boundaries in a pure data-driven manner.

最近，使用自动编码器（由使用神经网络建模的编码器，渠道和解码器组成）的通信系统的端到端学习问题最近被证明是一种有希望的方法。实际采用这种学习方法面临的挑战是，在变化的渠道条件（例如无线链接）下，它需要经常对自动编码器进行重新训练，以保持低解码错误率。由于重新培训既耗时又需要大量样本，因此当通道分布迅速变化时，它变得不切实际。我们建议使用不更改编码器和解码器网络的快速和样本（几射击）域的适应方法来解决此问题。不同于常规的训练时间无监督或半监督域的适应性，在这里，我们有一个训练有素的自动编码器，来自源分布，我们希望（在测试时间）使用仅使用一个小标记的数据集和无标记的数据来适应（测试时间）到目标分布。我们的方法着重于基于高斯混合物网络的通道模型，并根据类和组件条件仿射变换制定其适应性。学习的仿射转换用于设计解码器的最佳输入转换以补偿分布变化，并有效地呈现在接近源分布的解码器输入中。在实际MMWAVE FPGA设置以及无线设置共有的许多模拟分布变化上，使用非常少量的目标域样本来证明我们方法在适应时的有效性。

Link-Adaptation（LA）是无线通信的最重要方面之一，其中发射器使用的调制和编码方案（MCS）适用于通道条件，以满足某些目标误差率。在具有离细胞外干扰的单用户SISO（SU-SISO）系统中，LA是通过计算接收器处计算后平均值 - 交换后噪声比（SINR）进行的。可以在使用线性探测器的多用户MIMO（MU-MIMO）接收器中使用相同的技术。均衡后SINR的另一个重要用途是用于物理层（PHY）抽象，其中几个PHY块（例如通道编码器，检测器和通道解码器）被抽象模型取代，以加快系统级级别的模拟。但是，对于具有非线性接收器的MU-MIMO系统，尚无等效于平衡后的SINR，这使LA和PHY抽象都极具挑战性。这份由两部分组成的论文解决了这个重要问题。在这一部分中，提出了一个称为检测器的称为比特 - 金属解码速率（BMDR）的度量，该指标提出了相当于后平等SINR的建议。由于BMDR没有封闭形式的表达式可以启用其瞬时计算，因此一种机器学习方法可以预测其以及广泛的仿真结果。

这本数字本书包含在物理模拟的背景下与深度学习相关的一切实际和全面的一切。尽可能多，所有主题都带有Jupyter笔记本的形式的动手代码示例，以便快速入门。除了标准的受监督学习的数据中，我们将看看物理丢失约束，更紧密耦合的学习算法，具有可微分的模拟，以及加强学习和不确定性建模。我们生活在令人兴奋的时期：这些方法具有从根本上改变计算机模拟可以实现的巨大潜力。

最近，基于深层神经网络（DNN）的物理层通信技术引起了极大的兴趣。尽管模拟实验已经验证了它们增强通信系统和出色性能的潜力，但对理论分析的关注很少。具体而言，物理层中的大多数研究都倾向于专注于DNN模型在无线通信问题上的应用，但理论上不了解DNN在通信系统中的工作方式。在本文中，我们旨在定量分析为什么DNN可以在物理层中与传统技术相比，并在计算复杂性方面提高其成本。为了实现这一目标，我们首先分析基于DNN的发射器的编码性能，并将其与传统发射器进行比较。然后，我们理论上分析了基于DNN的估计器的性能，并将其与传统估计器进行比较。第三，我们调查并验证在信息理论概念下基于DNN的通信系统中如何播放信息。我们的分析开发了一种简洁的方式，可以在物理层通信中打开DNN的“黑匣子”，可用于支持基于DNN的智能通信技术的设计，并有助于提供可解释的性能评估。

In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. First, we present a realization pipeline showing the conversion of the models from Python libraries to the FPGA chip synthesis and implementation. Then, we review the main alternatives for the hardware implementation of nonlinear activation functions. The main results are divided into three parts: a performance comparison, an analysis of how activation functions are implemented, and a report on the complexity of the hardware. The performance in Q-factor is presented for the cases of bidirectional long-short-term memory coupled with convolutional NN (biLSTM + CNN) equalizer, CNN equalizer, and standard 1-StpS digital back-propagation (DBP) for the simulation and experiment propagation of a single channel dual-polarization (SC-DP) 16QAM at 34 GBd along 17x70km of LEAF. The biLSTM+CNN equalizer provides a similar result to DBP and a 1.7 dB Q-factor gain compared with the chromatic dispersion compensation baseline in the experimental dataset. After that, we assess the Q-factor and the impact of hardware utilization when approximating the activation functions of NN using Taylor series, piecewise linear, and look-up table (LUT) approximations. We also show how to mitigate the approximation errors with extra training and provide some insights into possible gradient problems in the LUT approximation. Finally, to evaluate the complexity of hardware implementation to achieve 400G throughput, fixed-point NN-based equalizers with approximated activation functions are developed and implemented in an FPGA.

最近的作品表明，可以通过使用机器学习技术来学习图像的无线传输的任务。已经通过训练了自动化器，非常有前沿图像质量，优于利用源和信道编码分离的流行数字方案，以具有中间的不可培训的沟道层，优于利用源和信道编码分离。然而，这些方法假设可以通过信道传输任何复数，这可以防止硬件或协议只能承认某些信道输入的场景中的算法，例如使用数字星座的使用。这里，我们提出了DeepJSCC-Q，用于无线图像传输的端到端优化的联合源信道编码方案，其能够用固定信道输入字母操作。我们表明DeepJSCC-Q可以对使用连续值通道输入的模型来实现类似的性能。重要的是，在信道条件恶化的情况下，保留在现有工作中观察到的图像质量的正常劣化，使DeepJSCC-Q在实际系统中部署更具吸引力。

正交频分复用（OFDM）已广泛应用于当前通信系统。人工智能（AI）addm接收器目前被带到最前沿替换和改进传统的OFDM接收器。在这项研究中，我们首先比较两个AI辅助OFDM接收器，即数据驱动的完全连接的深神经网络和模型驱动的COMNet，通过广泛的仿真和实时视频传输，使用5G快速原型制作系统进行跨越式-Air（OTA）测试。我们在离线训练和真实环境之间的频道模型之间的差异差异导致的模拟和OTA测试之间找到了性能差距。我们开发一种新颖的在线培训系统，称为SwitchNet接收器，以解决此问题。该接收器具有灵活且可扩展的架构，可以通过在线训练几个参数来适应真实频道。从OTA测试中，AI辅助OFDM接收器，尤其是SwitchNet接收器，对真实环境具有鲁棒，并且对未来的通信系统有前途。我们讨论了本文初步研究的潜在挑战和未来的研究。

Motivated by recent success of Machine Learning (ML) tools in wireless communications, the idea of semantic communication by Weaver from 1949 has received considerable attention. It breaks with the classic design paradigm of Shannon by aiming to transmit the meaning of a message, i.e., semantics, rather than its exact copy and thus allows for savings in channel uses or information rate. In this work, we extend the fundamental approach from Basu et al. for modeling semantics from logical to probabilistic entailment relations between meaning and messages. Thus, we model semantics by means of a hidden random variable and define the task of semantic communication as transmission of messages over a communication channel such that semantics is best preserved. We formulate the semantic communication design either as an Information Maximization or as an Information Bottleneck optimization problem. Finally, we propose the ML-based semantic communication system SINFONI for a distributed multipoint scenario: SINFONI communicates the meaning behind multiple messages that are observed at different senders to a single receiver for semantic retrieval. We analyze SINFONI by processing images as an example of messages. Numerical results reveal a tremendous rate normalized SNR shift up to 20 dB compared to classically designed communication systems.

这项正在进行的工作旨在为统计学习提供统一的介绍，从诸如GMM和HMM等经典模型到现代神经网络（如VAE和扩散模型）缓慢地构建。如今，有许多互联网资源可以孤立地解释这一点或新的机器学习算法，但是它们并没有（也不能在如此简短的空间中）将这些算法彼此连接起来，或者与统计模型的经典文献相连现代算法出现了。同样明显缺乏的是一个单一的符号系统，尽管对那些已经熟悉材料的人（如这些帖子的作者）不满意，但对新手的入境造成了重大障碍。同样，我的目的是将各种模型（尽可能）吸收到一个用于推理和学习的框架上，表明（以及为什么）如何以最小的变化将一个模型更改为另一个模型（其中一些是新颖的，另一些是文献中的）。某些背景当然是必要的。我以为读者熟悉基本的多变量计算，概率和统计以及线性代数。这本书的目标当然不是​​完整性，而是从基本知识到过去十年中极强大的新模型的直线路径或多或少。然后，目标是补充而不是替换，诸如Bishop的\ emph {模式识别和机器学习}之类的综合文本，该文本现在已经15岁了。