Laura Brink

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2018-177

December 14, 2018

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-177.pdf

We apply the techniques from meta-learning and machine learning to the communications domain. Specifically, we explore how neural networks can learn to equalize new channel environments without training on them and how neural networks can learn to estimate and correct carrier frequency offset for new rates of rotation without training on them. We show that deep neural networks can learn to learn to estimate channel taps for two tap channels. We also explore how deep recursive neural networks learn to learn to equalize for any given channel. We demonstrate that neural networks can learn to learn to estimate and correct carrier frequency offset for new rates of rotation. Crucially, we do all of this without using backpropagation to re-train the networks for each new set of environmental conditions.

Advisors: Anant Sahai


BibTeX citation:

@mastersthesis{Brink:EECS-2018-177,
    Author= {Brink, Laura},
    Editor= {Sahai, Anant and Wawrzynek, John},
    Title= {Deep Networks for Equalization in Communications},
    School= {EECS Department, University of California, Berkeley},
    Year= {2018},
    Month= {Dec},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-177.html},
    Number= {UCB/EECS-2018-177},
    Abstract= {We apply the techniques from meta-learning and machine learning to the communications domain. Specifically, we explore how neural networks can learn to equalize new channel environments without training on them and how neural networks can learn to estimate and correct carrier frequency offset for new rates of rotation without training on them. We show that deep neural networks can learn to learn to estimate channel taps for two tap channels. We also explore how deep recursive neural networks learn to learn to equalize for any given channel. We demonstrate that neural networks can learn to learn to estimate and correct carrier frequency offset for new rates of rotation. Crucially, we do all of this without using backpropagation to re-train the networks for each new set of environmental conditions.},
}

EndNote citation:

%0 Thesis
%A Brink, Laura 
%E Sahai, Anant 
%E Wawrzynek, John 
%T Deep Networks for Equalization in Communications
%I EECS Department, University of California, Berkeley
%D 2018
%8 December 14
%@ UCB/EECS-2018-177
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-177.html
%F Brink:EECS-2018-177