4 Hits in 0.45 sec

DeepTurbo: Deep Turbo Decoder [article]

Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
2019 arXiv   pre-print
We focus on Turbo codes and propose DeepTurbo, a novel deep learning based architecture for Turbo decoding.  ...  Here we remedy this requirement and propose a fully end-to-end trained neural decoder - Deep Turbo Decoder (DeepTurbo).  ...  DEEP TURBO DECODER PERFORMANCE We compare the performance of Deep Turbo Decoder (DEEPTURBO) with the baseline decoders, the standardTurbo A.  ... 
arXiv:1903.02295v2 fatcat:ritve3qsljaytcwjspkkei63b4

Neural Network-Aided BCJR Algorithm for Joint Symbol Detection and Channel Decoding [article]

Wen-Chiao Tsai, Chieh-Fang Teng, Han-Mo Ou, An-Yeu Wu
2020 arXiv   pre-print
In this work, we propose a BCJR receiver for joint symbol detection and channel decoding.  ...  Recently, deep learning-assisted communication systems have achieved many eye-catching results and attracted more and more researchers in this emerging field.  ...  As in the Turbo decoder, the BCJR receiver is composed of two BCJR decoders.  ... 
arXiv:2006.01125v2 fatcat:rinv7tqvbzeqxmu25i6gleifzi

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

Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
2019 arXiv   pre-print
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  ...  TurboAE shows that the development of channel coding design can be automated via deep learning, with near-optimal performance.  ...  We compare two benchmarks: (1) canonical Turbo code, and (2) DeepTurbo Decoder [24] , a neural decoder fine-tuned at the given channel.  ... 
arXiv:1911.03038v1 fatcat:zqzosaydmvhl3hnfnbshtwuiim

Model-Driven DNN Decoder for Turbo Codes: Design, Simulation and Experimental Results [article]

Yunfeng He, Jing Zhang, Shi Jin, Chao-Kai Wen, Geoffrey Ye Li
2020 arXiv   pre-print
This paper presents a novel model-driven deep learning (DL) architecture, called TurboNet, for turbo decoding that integrates DL into the traditional max-log-maximum a posteriori (MAP) algorithm.  ...  To design the TurboNet, the original iterative structure is unfolded as deep neural network (DNN) decoding units, where trainable weights are introduced to the max-log-MAP algorithm and optimized through  ...  The structures of turbo encoder and decoder.  ... 
arXiv:2006.08896v1 fatcat:4ioqzb5d55ayfhfj5tbdtznady