Source Coding for Text Transmission using a Deep Neural Network as a Lossy Compression Stage

F Lara, J Arellano, M Castillo, L Topón… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
… several source coding techniques and research works proposed previously. For instance,
in [5] a joint source and channel coding scheme is proposed using Text Embedding Neural

Multi-tones' phase coding (mtpc) of interaural time difference by spiking neural network

Z Pan, M Zhang, J Wu, H Li - arXiv preprint arXiv:2007.03274, 2020 - arxiv.org
… [25] propose that our neuronal system locates the sound source by mapping the binaural
location-specific sounds to two synchronous spiking patterns, which are derived from spatio-…

End-to-end learning of neuromorphic wireless systems for low-power edge artificial intelligence

N Skatchkovsky, H Jang… - 2020 54th Asilomar …, 2020 - ieeexplore.ieee.org
… training SNNs and wireless channel impairments. Recent work has demonstrated the potential
of joint sourcechannel coding based on conventional (non-spiking) neural networks. With …

Ensemble representations reveal distinct neural coding of visual working memory

BI Oh, YJ Kim, MS Kang - Nature communications, 2019 - nature.com
… We characterized the population-level neural coding of … Here, we consistently observe stable
coding of simple features … coded over time, whereas neural coding of the ensemble mean is …

Deepcode: Feedback codes via deep learning

H Kim, Y Jiang, S Kannan, S Oh… - Advances in neural …, 2018 - proceedings.neurips.cc
… years apply deep learning for channel coding, very few of … -time complexity of the neural
network architectures. Our main … family of RNN-driven neural codes that have three orders of …

Learning joint detection, equalization and decoding for short-packet communications

S Dörner, J Clausius, S Cammerer… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… For this, we extend the recently proposed serial Turbo-autoencoder neural network (NN) …
that can compete with state-of-the-art short length channel codes or even outperform state-of…

Doubly residual neural decoder: Towards low-complexity high-performance channel decoding

S Liao, C Deng, M Yin, B Yuan - … of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
neural channel decoders for the existing widely used channel codes (such as LDPC, Polar
and BCH codes). … This paper focuses efficient neural channel decoder design for block codes, …

Neural Compress-and-Forward for the Relay Channel

E Ozyilkan, F Carpi, S Garg, E Erkip - arXiv preprint arXiv:2404.14594, 2024 - arxiv.org
… Recent learning approaches for the relay channel [16], [17] considered a joint source-channel
setting, where the former focused on image transmission via joint source-channel coding, …

Deep learning-constructed joint transmission-recognition for Internet of Things

CH Lee, JW Lin, PH Chen, YC Chang - IEEE Access, 2019 - ieeexplore.ieee.org
… Since the state-of-the-art recognition is achieved by applying deep neural networks (DNNs)
and it has recently been shown that channel codes and joint source-channel coding can …

[PDF][PDF] Low-memory end-to-end training for iterative joint speech dereverberation and separation with a neural source model

K Saijo, R Scheibler - arXiv preprint ArXiv:2110.06545, 2021 - researchgate.net
… multichannel joint dereverberation and source separation with a neural source model. We
… of ILRMA-T with a deep neural network (DNN) serving as source model. The weights of the …