TinyTurbo: Efficient Turbo Decoders on Edge
Not on the map. Why?
Abstract (arXiv)
In this paper, we introduce a neural-augmented decoder for Turbo codes called TINYTURBO . TINYTURBO has complexity comparable to the classical max-log-MAP algorithm but has much better reliability than the max-log-MAP baseline and performs close to the MAP algorithm. We show that TINYTURBO exhibits strong robustness on a variety of practical channels of interest, such as EPA and EVA channels, which are included in the LTE standards. We also show that TINYTURBO strongly generalizes across different rate, blocklengths, and trellises. We verify the reliability and efficiency of TINYTURBO via over-the-air experiments.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 13 of its 28 references that are in the map. First posted on arXiv 30 Sep 2022.
Builds on
13 of 28 references.
References · 13
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020Model-Based Deep Learningcited by 141
- 2016Learning to Decode Linear Codes Using Deep Learningcited by 61
- 2018Communication Algorithms via Deep Learningcited by 42
- 2017An Iterative BP-CNN Architecture for Channel Decodingcited by 18
- 2021KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learningcited by 17
- 2021Cyclically Equivariant Neural Decoders for Cyclic Codescited by 12
- 2019Deep Learning-based Polar Code Designcited by 10
- 2020Pruning Neural Belief Propagation Decoderscited by 10
- 2018LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networkscited by 9
- 2019DeepTurbo: Deep Turbo Decodercited by 9
- 2018Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanismcited by 8
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 2.
3 papers.