M to 1 Joint Source-Channel Coding of Gaussian Sources via Dichotomy of the Input Space Based on Deep Learning

In this paper, we propose a deep neural network framework for Joint Source-Channel Coding of an m dimensional i.i.d. Gaussian source for transmission over a single additive white Gaussian noise channel with no delay. The framework employs two neural encoder-decoder pairs that learn to split the inpu...

Full description

Bibliographic Details

Published in:	DCC (Los Alamitos, Calif.) pp. 488 - 497
Main Authors:	Saidutta, Yashas Malur, Abdi, Afshin, Fekri, Faramarz
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.03.2019
Subjects:	AWGN Channel Channel coding Decoding Deep Learning Deep Neural Networks Gaussian Source Image coding Joint Source Channel Coding Neural networks Spirals Transmitters
ISSN:	2375-0359
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!