ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Autoencoder based Robust Transceivers for Fading Channels using Deep Neural Networks

Mattu, SR and Lakshmi Narasimhan, T and Chockalingam, A (2020) Autoencoder based Robust Transceivers for Fading Channels using Deep Neural Networks. In: 91st IEEE Vehicular Technology Conference, VTC Spring 2020, 25-28 May 2020, Antwerp; Belgium.

[img] PDF
IEEE_VEH_TEC_2020_2020.pdf - Published Version
Restricted to Registered users only

Download (145kB) | Request a copy
Official URL: https://dx.doi.org/10.1109/VTC2020-Spring48590.202...

Abstract

In this paper, we design transceivers for fading channels using autoencoders and deep neural networks (DNN). Specifically, we consider the problem of finding (n, k) block codes such that the codewords are maximally separated in terms of their Hamming distance using autoencoders. We design an encoder and robust decoder for these block codes using DNNs. Towards this, we propose a novel training methodology for the DNN that attempts to maximize the minimum Hamming distance between codewords. We propose a loss function for this training which has stable weight updates during back propagation compared to other loss functions reported in the literature. The block codes learned using the proposed methodology are found to achieve the maximal Hamming distance separation that is known in theory. We also propose two different receiver architectures based on fully connected deep neural network (FCDNN) and bidirectional recurrent neural network (BRNN) that are suited for complex fading channels. The proposed DNN based receiver is shown to achieve significantly better error performance when compared to their classical counterparts in the presence of channel model mismatches. In the presence of model mismatches such as imperfect channel knowledge and noise correlation, the proposed DNN based transceiver is shown to offer increased reliability and robustness than the conventional transceiver. © 2020 IEEE.

Item Type: Conference Paper
Publication: IEEE Vehicular Technology Conference
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: cited By 0; Conference of 91st IEEE Vehicular Technology Conference, VTC Spring 2020 ; Conference Date: 25 May 2020 Through 28 May 2020; Conference Code:161536
Keywords: Backpropagation; Block codes; Deep neural networks; Fading channels; Hamming distance; Learning systems; Springs (components); Transceivers, Bidirectional recurrent neural networks; Classical counterpart; Complex fading channels; Imperfect channel knowledge; Minimum hamming distances; Receiver architecture; Reliability and robustness; Robust transceivers, Recurrent neural networks
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 23 Nov 2020 07:29
Last Modified: 23 Nov 2020 07:29
URI: http://eprints.iisc.ac.in/id/eprint/66174

Actions (login required)

View Item View Item