ConvAE: A New Channel Autoencoder Based on Convolutional Layers and Residual Connections
- 22 July 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 23 (10) , 1769-1772
Abstract
In this paper, we propose ConvAE, a new channel autoencoder structure. ConvAE uses residual blocks with convolutional layers. This configuration increases performance while decreasing computational complexity at run-time compared to conventional channel autoencoders. Simulations using both conventional and proposed autoencoders for a 2-by-2 multiple-input multiple-output (MIMO) system under Rayleigh and Nakagami-m fading show that ConvAE is able to attain a lower bit error rate and higher achievable rate relative to conventional channel autoencoder schemes.Keywords
Funding Information
- Institute of Information & Communications Technology Planning & Evaluation
- National Research Foundation of Korea (2019-0-00500)
This publication has 7 references indexed in Scilit:
- Physical Layer Communications System Design Over-the-Air Using Adversarial Networks2018
- Unsupervised Deep Learning for MU-SIMO Joint Transmitter and Noncoherent Receiver DesignIEEE Wireless Communications Letters, 2018
- Deep Learning for an Effective Nonorthogonal Multiple Access SchemeIEEE Transactions on Vehicular Technology, 2018
- A Novel PAPR Reduction Scheme for OFDM System Based on Deep LearningIEEE Communications Letters, 2017
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention2016
- Deep Residual Learning for Image Recognition2016