Error Correction Code Transformer

BCH(7,4) code with N = 6, d = 32, similarly to the results presented in Section 6.1. Interestingly, in the early stage of the decoding, ECCT seems to focus its processing of the syndrome. Once the network corrects the bit (last layers(s)), the values return to normal. Using multiple heads is clearly beneficial for the model's performance. The proposed shallow ECCTs are able to compete and even surpass the SCL for some of the codes and SNRs.