Learning from the Syndrome

Abstract

In this paper, we introduce the syndrome loss, an alternative loss function for neural error-correcting decoders based on a relaxation of the syndrome. The syndrome loss penalizes the decoder for producing outputs that do not correspond to valid codewords. We show that training with the syndrome loss yields decoders with consistently lower frame error rate for a number of short block codes, at little additional cost during training and no additional cost during inference. The proposed method does not depend on knowledge of the transmitted codeword, making it a promising tool for online adaptation to changing channel conditions.

Accepted to Asilomar 2018 - special session on "Machine Learning for Wireless Systems"

References in corpus (4)

• Deep Learning Methods for Improved Decoding of Linear Codes
• An Iterative BP-CNN Architecture for Channel Decoding
• RNN Decoding of Linear Block Codes
• Scaling Deep Learning-based Decoding of Polar Codes via Partitioning