An Iterative BP-CNN Architecture for Channel Decoding

Thursday, March 01, 2018
11:00am - 12:00pm
EER 0.806 / 0.808
Inspired by the recent advances in deep learning, we propose a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. The standard BP decoder is used to estimate the coded bits, followed by a CNN to remove the estimation errors of the BP decoder and obtain a more accurate estimation of the channel noise. Iterating between BP and CNN will gradually improve the decoding SNR and hence result in better decoding performance. To train a well-behaved CNN model, we define a new loss function which involves not only the accuracy of the noise estimation but also the normality test for the estimation errors, i.e., to measure how likely the estimation errors follow a Gaussian distribution. The introduction of the normality test to the CNN training shapes the residual noise distribution and further reduces the BER of the iterative decoding, compared to using the standard quadratic loss function. We carry out extensive experiments to analyze and verify the proposed framework.


Cong Shen
University of Science and Technology of China

Cong Shen received his B.S. and M.S. degrees, in 2002 and 2004 respectively, from the Department of Electronic Engineering, Tsinghua University, China. He obtained the Ph.D. degree from the Electrical Engineering Department, UCLA, in 2009. From 2009 to 2014, He worked for Qualcomm Research in San Diego, CA, focusing on Cognitive Radio, TV White Space, Heterogeneous Networks (HetNet), and Ultra-Dense Networks (UDN). In 2015, he returned to academia and joined University of Science and Technology of China (USTC) as Professor in the School of Information Science and Technology. His research interests include machine learning and wireless communications. He currently serves as an editor for the IEEE Transactions on Wireless Communications.