%0 Generic %1 clausius2023optimizing %A Clausius, Jannis %A Geiselhart, Marvin %A ten Brink, Stephan %D 2023 %K %T Optimizing Serially Concatenated Neural Codes with Classical Decoders %U https://arxiv.org/abs/2212.10355 %X For improving short-length codes, we demonstrate that classic decoders can also be used with real-valued, neural encoders, i.e., deep-learning based codeword sequence generators. Here, the classical decoder can be a valuable tool to gain insights into these neural codes and shed light on weaknesses. Specifically, the turbo-autoencoder is a recently developed channel coding scheme where both encoder and decoder are replaced by neural networks. We first show that the limited receptive field of convolutional neural network (CNN)-based codes enables the application of the BCJR algorithm to optimally decode them with feasible computational complexity. These maximum a posteriori (MAP) component decoders then are used to form classical (iterative) turbo decoders for parallel or serially concatenated CNN encoders, offering a close-to-maximum likelihood (ML) decoding of the learned codes. To the best of our knowledge, this is the first time that a classical decoding algorithm is applied to a non-trivial, real-valued neural code. Furthermore, as the BCJR algorithm is fully differentiable, it is possible to train, or fine-tune, the neural encoder in an end-to-end fashion.

@misc{clausius2023optimizing, abstract = {For improving short-length codes, we demonstrate that classic decoders can also be used with real-valued, neural encoders, i.e., deep-learning based codeword sequence generators. Here, the classical decoder can be a valuable tool to gain insights into these neural codes and shed light on weaknesses. Specifically, the turbo-autoencoder is a recently developed channel coding scheme where both encoder and decoder are replaced by neural networks. We first show that the limited receptive field of convolutional neural network (CNN)-based codes enables the application of the BCJR algorithm to optimally decode them with feasible computational complexity. These maximum a posteriori (MAP) component decoders then are used to form classical (iterative) turbo decoders for parallel or serially concatenated CNN encoders, offering a close-to-maximum likelihood (ML) decoding of the learned codes. To the best of our knowledge, this is the first time that a classical decoding algorithm is applied to a non-trivial, real-valued neural code. Furthermore, as the BCJR algorithm is fully differentiable, it is possible to train, or fine-tune, the neural encoder in an end-to-end fashion.}, added-at = {2023-07-19T14:05:12.000+0200}, archiveprefix = {arXiv}, author = {Clausius, Jannis and Geiselhart, Marvin and ten Brink, Stephan}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/21c4f9a07603573d3eee04905de666a74/jannisclausius}, eprint = {2212.10355}, interhash = {4eeff69d11b50b73b7de2977902cabaf}, intrahash = {1c4f9a07603573d3eee04905de666a74}, keywords = {}, primaryclass = {cs.IT}, timestamp = {2023-07-19T14:05:12.000+0200}, title = {Optimizing Serially Concatenated Neural Codes with Classical Decoders}, url = {https://arxiv.org/abs/2212.10355}, year = 2023 }