TinyTurbo: Efficient Turbo Decoders on Edge
This work addresses the need for efficient and reliable communication decoding in edge computing, offering a domain-specific incremental improvement over existing methods.
The paper tackles the problem of improving Turbo code decoding efficiency and reliability for edge devices by introducing TinyTurbo, a neural-augmented decoder that achieves complexity comparable to max-log-MAP with much better reliability, performing close to MAP and demonstrating robustness on LTE channels like EPA and EVA.
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.