Neural Network Coding

TL;DR

Neural Network Coding (NNC) is a data-driven, adaptable joint source and network coding approach using neural networks, demonstrating improved performance over traditional methods in transmitting correlated data over noisy networks.

Contribution

This paper introduces NNC, a novel neural network-based scheme for joint source and network coding that adapts to arbitrary topologies and source statistics without prior assumptions.

Findings

NNC outperforms baseline schemes in low-SNR conditions.

NNC effectively transmits correlated sources like MNIST images.

The approach adapts to various network topologies and power constraints.

Abstract

In this paper we introduce Neural Network Coding(NNC), a data-driven approach to joint source and network coding. In NNC, the encoders at each source and intermediate node, as well as the decoder at each destination node, are neural networks which are all trained jointly for the task of communicating correlated sources through a network of noisy point-to-point links. The NNC scheme is application-specific and makes use of a training set of data, instead of making assumptions on the source statistics. In addition, it can adapt to any arbitrary network topology and power constraint. We show empirically that, for the task of transmitting MNIST images over a network, the NNC scheme shows improvement over baseline schemes, especially in the low-SNR regime.