Trainable Communication Systems: Concepts and Prototype

by   Sebastian Cammerer, et al.

We consider a trainable point-to-point communication system, where both transmitter and receiver are implemented as neural networks (NNs), and demonstrate that training on the bit-wise mutual information (BMI) allows seamless integration with practical bit-metric decoding (BMD) receivers, as well as joint optimization of constellation shaping and labeling. Moreover, we present a fully differentiable neural iterative demapping and decoding (IDD) structure which achieves significant gains on additive white Gaussian noise (AWGN) channels using a standard 802.11n low-density parity-check (LDPC) code. The strength of this approach is that it can be applied to arbitrary channels without any modifications. Going one step further, we show that careful code design can lead to further performance improvements. Lastly, we show the viability of the proposed system through implementation on software-defined radios (SDRs) and training of the end-to-end system on the actual wireless channel. Experimental results reveal that the proposed method enables significant gains compared to conventional techniques.



page 1

page 2

page 3

page 4


Model-free Training of End-to-end Communication Systems

The idea of end-to-end learning of communication systems through neural ...

End-to-end Learning for OFDM: From Neural Receivers to Pilotless Communication

Previous studies have demonstrated that end-to-end learning enables sign...

Impulsive Noise Mitigation in Powerline Communications Using Sparse Bayesian Learning

Additive asynchronous and cyclostationary impulsive noise limits communi...

Deep Reinforcement Learning Autoencoder with Noisy Feedback

End-to-end learning of communication systems enables joint optimization ...

End-to-end Waveform Learning Through Joint Optimization of Pulse and Constellation Shaping

As communication systems are foreseen to enable new services such as joi...

Robust Wireless Fingerprinting via Complex-Valued Neural Networks

A "wireless fingerprint" which exploits hardware imperfections unique to...

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

We demonstrate that error correcting codes (ECCs) can be used to constru...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.