Communication systems using neural network-based transceivers with autoencoder-driven end-to-end learning

使用基于神经网络的收发器和自动编码器驱动的端到端学习的通信系统

• 批准号: 402834551
• 负责人: Professor Dr.-Ing. Stephan ten Brink
• 金额: --
• 依托单位: Institut für Nachrichtenübertragung (INÜ)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2018
• 资助国家: 德国
• 起止时间: 2017-12-31 至 2021-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/402834551?language=en
• 关键词: Communication; systems; using; neural; network

The fields of machine learning and, in particular, deep learning have seen very rapid growth during the past few years; their applications now extend into almost every industry and research domain. Although researchers have tried to address communications-related problems with machine learning in the past, it still has had no fundamental impact on the way we design and implement communications systems today. At first glance, machine learning techniques do not appear to be a good match to communications on the physical layer, with 50 years of tremendous progress based on "classic" signal processing, communication and information theory, approaching close-to-optimal Shannon limit performance on many channels. However, several open problems remain, e.g. pertaining adaptivity and complexity of joint processing, where first results using machine learning-based approaches are promising. This proposal seeks to examine learnable end-to-end communications based on the "autoencoder" concept and deep learning techniques. It promises a communications system that can learn to communicate over any type of channel without the need for detailed prior mathematical abstraction of the channel model, breaking up restrictions commonplace in conventional block-based signal processing by moving away from handcrafted, carefully optimized sub-blocks towards adaptive and flexible (artificial) neural networks, leading to many attractive research questions. To obtain a more comprehensive understanding of the potential of machine learning techniques for communications, we start off from classic signal processing as a reference; then we study neural networks using conventional block-based learning (replacing, e.g. classic modulation, detection, or equalization blocks, ...), until finally arriving at multi-block neural networks based on autoencoder-driven end-to-end learning. We also plan to validate the explored concepts by over-the-air measurements, giving rise to many effects on the communication channel that cannot be found in many classical models, and, thus, need to be learned implicitly. The benefits of machine learning approaches may include more flexible hardware, highly adaptive systems and less overall complexity. We thus pose the seemingly naive, yet, in fact, rather complicated and attractive research question: "Can we learn to communicate?"Note that this proposal targets physical layer transmission without any further respect to the semantics of the message itself (i.e. no “understanding” of the message or its content is trained).

在过去的几年里，机器学习领域，特别是深度学习领域的发展非常迅速;它们的应用现在已经扩展到几乎所有的行业和研究领域。尽管研究人员过去曾试图用机器学习来解决与通信相关的问题，但它仍然没有对我们今天设计和实现通信系统的方式产生根本性的影响。乍一看，机器学习技术似乎并不适合物理层上的通信，50年来基于“经典”信号处理，通信和信息理论的巨大进步，在许多信道上接近最佳香农极限性能。然而，仍然存在一些开放的问题，例如，联合处理的自适应性和复杂性，其中使用基于机器学习的方法的第一个结果是有希望的。该提案旨在研究基于“自动编码器”概念和深度学习技术的可学习端到端通信。它承诺一个通信系统，可以学习在任何类型的信道上进行通信，而不需要信道模型的详细的先验数学抽象，通过从手工制作的，精心优化的子块转向自适应和灵活的（人工）神经网络，打破了传统的基于块的信号处理中常见的限制，导致许多有吸引力的研究问题。为了更全面地了解机器学习技术在通信中的潜力，我们从经典信号处理开始作为参考;然后我们使用传统的基于块的学习来研究神经网络（例如，替代经典调制，检测或均衡块），直到最终达到基于自动编码器驱动的端到端学习的多块神经网络。我们还计划通过空中测量来验证所探索的概念，从而对通信信道产生许多影响，这些影响在许多经典模型中找不到，因此需要隐式学习。机器学习方法的好处可能包括更灵活的硬件，高度自适应的系统和更低的整体复杂性。因此，我们提出了一个看似天真，但实际上相当复杂和有吸引力的研究问题：“我们能学会沟通吗？请注意，该建议的目标是物理层传输，而不进一步考虑消息本身的语义（即没有训练对消息或其内容的“理解”）。

项目成果

Trainable Communication Systems: Concepts and Prototype

• DOI: 10.1109/tcomm.2020.3002915
• 发表时间: 2019-11
• 期刊: IEEE Transactions on Communications
• 影响因子: 8.3
• 作者: Sebastian Cammerer;Fayçal Ait Aoudia;Sebastian Dörner;Maximilian Stark;J. Hoydis;S. ten Brink

On Recurrent Neural Networks for Sequence-based Processing in Communications

通信中基于序列处理的循环神经网络

• DOI: 10.1109/ieeeconf44664.2019.9048728
• 发表时间: 2019
• 期刊: 2019 53rd Asilomar Conference on Signals, Systems, and Computers
• 作者: Daniel Tandler;Sebastian Dörner;Sebastian Cammerer;Stephan ten Brink
• 通讯作者: Stephan ten Brink

Serial vs. Parallel Turbo-Autoencoders and Accelerated Training for Learned Channel Codes

串行与并行 Turbo 自动编码器以及学习通道代码的加速训练

• DOI: 10.1109/istc49272.2021.9594130
• 发表时间: 2021
• 期刊: 2021 11th International Symposium on Topics in Coding (ISTC
• 作者: Jannis Clausius;Sebastian Dörner;Sebastian Cammerer;Stephan ten Brink
• 通讯作者: Stephan ten Brink

Online Label Recovery for Deep Learning-based Communication through Error Correcting Codes

• DOI: 10.1109/iswcs.2018.8491189
• 发表时间: 2018-07
• 期刊: 2018 15th International Symposium on Wireless Communication Systems (ISWCS)
• 作者: Stefan Schibisch;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink

OFDM-Autoencoder for End-to-End Learning of Communications Systems

• DOI: 10.1109/spawc.2018.8445920
• 发表时间: 2018-03
• 期刊: 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
• 作者: Alexander Felix;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink