mlsanityData to 7 Oct 2026

Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels

arXiv 1911.03038 ↗First posted 8 Nov 2019cs.IT cs.LG eess.SPcited by 42

Not on the map. Why?

Abstract (arXiv)

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians for communicating under canonical models after over 60 years of research. On the other hand, in many non-canonical channel settings, optimal codes do not exist and the codes designed for canonical models are adapted via heuristics to these channels and are thus not guaranteed to be optimal. In this work, we make significant progress on this problem by designing a fully end-to-end jointly trained neural encoder and decoder, namely, Turbo Autoencoder (TurboAE), with the following contributions: (a) under moderate block lengths, TurboAE approaches state-of-the-art performance under canonical channels; (b) moreover, TurboAE outperforms the state-of-the-art codes under non-canonical settings in terms of reliability. TurboAE shows that the development of channel coding design can be automated via deep learning, with near-optimal performance.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 5; 2023: 9; 2024: 5; 2025: 5; 2026: 4.

42 papers.

Sort:

By area:

  1. 2021KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learningcited by 16
  2. 2021Autoregressive Belief Propagation for Decoding Block Codescited by 15
  3. 2021ProductAE: Towards Training Larger Channel Codes based on Neural Product Codescited by 14
  4. 2021Neural Distributed Source Codingcited by 13
  5. 2021Cyclically Equivariant Neural Decoders for Cyclic Codescited by 12
  6. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  7. 2024Learning Linear Block Error Correction Codescited by 8
  8. 2021SVD-Embedded Deep Autoencoder for MIMO Communicationscited by 5
  9. 2022Concatenated Classic and Neural (CCN) Codes: ConcatenatedAEcited by 5
  10. 2022CRISP: Curriculum based Sequential Neural Decoders for Polar Code Familycited by 5
  11. 2023Diffusion Models for Accurate Channel Distribution Generationcited by 5
  12. 2023Robust Non-Linear Feedback Coding via Power-Constrained Deep Learningcited by 4
30 more
  1. 2023Generalization Bounds for Neural Belief Propagation Decoderscited by 4
  2. 2021End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channelscited by 2
  3. 2021DeepIC: Coding for Interference Channels via Deep Learningcited by 2
  4. 2022Hybrid Neural Coded Modulation: Design and Training Methodscited by 2
  5. 2025MinGRU-Based Encoder for Turbo Autoencoder Frameworkscited by 2
  6. 2021Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decodingcited by 1
  7. 2021Improving the List Decoding Version of the Cyclically Equivariant Neural Decodercited by 1
  8. 2021Discriminative Mutual Information Estimators for Channel Capacity Learningcited by 1
  9. 2021List Autoencoder: Towards Deep Learning Based Reliable Transmission Over Noisy Channelscited by 1
  10. 2021RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codescited by 1
  11. 2022Optimizing Serially Concatenated Neural Codes with Classical Decoderscited by 1
  12. 2023Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodescited by 1
  13. 2023ProductAE: Toward Deep Learning Driven Error-Correction Codes of Large Dimensionscited by 1
  14. 2023Component Training of Turbo Autoencoderscited by 1
  15. 2023Quantum Autoencoders for Learning Quantum Channel Codescited by 1
  16. 2024DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learningcited by 1
  17. 2024Factor Graph Optimization of Error-Correcting Codes for Belief Propagation Decodingcited by 1
  18. 2026Generalization Bounds for Transformer Channel Decoderscited by 1
  19. 2021Recovering AES Keys with a Deep Cold Boot Attackcited by 0
  20. 2022Hybrid HMM Decoder For Convolutional Codes By Joint Trellis-Like Structure and Channel Priorcited by 0
  21. 2023Interpreting Training Aspects of Deep-Learned Error-Correcting Codescited by 0
  22. 2024Disturbance-based Discretization, Differentiable IDS Channel, and an IDS-Correcting Code for DNA-based Storagecited by 0
  23. 2024Quantification and Validation for Degree of Understanding in M2M Semantic Communicationscited by 0
  24. 2025Online Meta-Learning Channel Autoencoder for Dynamic End-to-end Physical Layer Optimizationcited by 0
  25. 2025Decoding for Punctured Convolutional and Turbo Codes: A Deep Learning Solution for Protocols Compliancecited by 0
  26. 2025Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communicationscited by 0
  27. 2025Learning Binary Autoencoder-Based Codes with Progressive Trainingcited by 0
  28. 2026On the Fragility of AI-Based Channel Decoders under Small Channel Perturbationscited by 0
  29. 2026MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codescited by 0
  30. 2026Short-Length Code Designs for Integrated Sensing and Communications: A Deep Learning Approachcited by 0