Learning from the Syndrome

2018/10/23 by Loren Lugosch, Warren J. Gross, Lugosch, Loren +1 · 2 citations
Computer Science · Engineering · #Advanced Wireless Communication Techniques #Algorithms and Data Compression #Error Correcting Code Techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1810.10902

openalex publication_date 2018/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Scaling Deep Learning-based Decoding of Polar Codes via Partitioning

Cited by

• Neural-Model-Augmented Hybrid NMS-OSD Decoders for Near-ML in Short Block Codes
• Interplay Between Belief Propagation and Transformer: Differential-Attention Message Passing Transformer

Related

• Unsupervised Learning for Neural Network-based Polar Decoder via Syndrome Loss
• Neural Decoding with Optimization of Node Activations
• Interplay Between Belief Propagation and Transformer: Differential-Attention Message Passing Transformer
• Deep Learning for Decoding of Linear Codes - A Syndrome-Based Approach
• Learned Decimation for Neural Belief Propagation Decoders