Serial vs. Parallel Turbo-Autoencoders and Accelerated Training for Learned Channel Codes
Preprint
Abstract
Attracted by its scalability towards practical codeword lengths, we revisit the idea of Turbo-autoencoders for end-to-end learning of PHY-Layer communications. For this, we study the existing concepts of Turbo-autoencoders from the literature and compare the concept with state-of-the-art classical coding schemes. We propose a new component-wise training algorithm based on the idea of Gaussian a priori distributions that reduces the overall training time by almost a magnitude. Further, we propose a new serial architecture inspired by classical serially concatenated Turbo code structures and show that a carefully optimized interface between the two component autoencoders is required. To the best of our knowledge, these serial Turbo autoencoder structures are the best known neural network based learned sequences that can be trained from scratch without any required expert knowledge in the domain of channel codes.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Trainable Communication Systems: Concepts and PrototypeIEEE Transactions on Communications, 2020
- LEARN Codes: Inventing Low-Latency Codes via Recurrent Neural NetworksIEEE Journal on Selected Areas in Information Theory, 2020
- Deepcode: Feedback Codes via Deep LearningIEEE Journal on Selected Areas in Information Theory, 2020
- ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol DetectionIEEE Transactions on Wireless Communications, 2020
- Deep Learning Based Communication Over the AirIEEE Journal of Selected Topics in Signal Processing, 2017
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Deep MIMO detection2017
- Channel Coding Rate in the Finite Blocklength RegimeIEEE Transactions on Information Theory, 2010
- Convergence Analysis and Optimal Scheduling for Multiple Concatenated CodesIEEE Transactions on Information Theory, 2005
- Convergence behavior of iteratively decoded parallel concatenated codesIEEE Transactions on Communications, 2001