A Novel Deep Learning Approach for Syndrome-Based Decoding of BCH Codes

A Novel Deep Learning Approach for Syndrome-Based Decoding of BCH Codes

In this letter, we present a new decoder based on syndrome, where a deep neural network (DNN) is used to ascertain the error pattern based on reliability and the received vector’s syndrome. The proposed algorithm finds the correct error pattern by repeatedly choosing the error position which has the highest confidence in that particular error pattern. Lastly, the aforementioned progresses takes place after each such error pattern position selection – the received vector is updated. The simulation results for (63,45) and (63,36) BCH codes prove that the new approach is more effective than the existing neural network decoders. Furthermore, this new decoder is also novel in that it can be used on any existing syndrome based DNN decoder in addition without the need for any retraining.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Read More