Log In Sign Up

Learning from the Syndrome

by   Loren Lugosch, et al.

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.


page 1

page 2

page 3

page 4


FAID Diversity via Neural Networks

Decoder diversity is a powerful error correction framework in which a co...

Intermediate Loss Regularization for CTC-based Speech Recognition

We present a simple and efficient auxiliary loss function for automatic ...

Reed-Muller Codes Achieve Capacity on BMS Channels

This paper considers the performance of long Reed-Muller (RM) codes tran...

Boost decoding performance of finite geometry LDPC codes with deep learning tactics

It was known a standard min-sum decoder can be unrolled as a neural netw...

Channel Input Adaptation via Natural Type Selection

For the model of communication through a discrete memoryless channel usi...

Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes

Polar codes can theoretically achieve very competitive Frame Error Rates...

Adversarial Neural Networks for Error Correcting Codes

Error correcting codes are a fundamental component in modern day communi...