… To do so, we consider a flexible class of codes parameterized by a neural network and
jointly optimize for the encoding and decoding procedure. This approach is inspired by recent …

… To do so, we consider a flexible class of codes parameterized by a neural network and
jointly optimize for the encoding and decoding procedure. This approach is inspired by recent …

… encoder and decoder functions by two convolutional neural … applications joint source and
channel coding (JSCC) is … near-optimal channel codes (eg LDPC, Turbo codes) are employed …

… Olshausen, “Joint source-channel coding with neural networks for analog data compression
and storage,” in 2018 Data Compression Conference, March 2018, pp. 147–156. [41] E. …

… coding networks. In this paper, motivated by the inherent connections between neural joint
source-channel coding … neural joint source-channel coding scheme. More specifically, on the …

… we develop a neural network architecture for joint sourcechannel coding of text. Our model
uses a … neural network (RNN) encoder, a binarization layer, the channel layer, and a decoder …

… combining the two coding steps, motivating the design of joint source-channel coding (JSCC) …
Recently, a method called DeepJSCC, which employs deep neural networks (DNNs) to …

… investigate joint source channel coding (JSCC) for wireless image transmission over multipath
fading channels… Yu, “Infomax neural joint source-channel coding via adversarial bit flip,” in …

… channel and correlated texts over a broadcast channel. As the separate source-channel
coding principle no longer holds in such scenarios, we propose a joint source-channel coding …

… [10] Yuxuan Song, Minkai Xu, Lantao Yu, Hao Zhou, Shuo Shao, and Yong Yu, “Infomax
neural joint source-channel coding via adversarial bit flip,” arXiv preprint arXiv:2004.01454, …