A Novel Iterative Decoding for Iterated Codes Using Classical and Convolutional Neural Networks

Forward error correction is crucial for communication, enabling error rate or required SNR reduction. Longer codes improve correction ratio. Iterated codes offer a solution for constructing long codes with a simple coder and decoder. However, a basic iterative code decoder cannot fully exploit the code’s potential, as some error patterns within its correction capacity remain uncorrected. We propose two neural network-assisted decoders: one based on a classical neural network, and the second employing a convolutional neural network. Based on conducted research, we proposed an iterative neural network-based decoder. The resulting decoder demonstrated significantly improved overall performance, exceeding that of the classical decoder, proving the efficient application of neural networks in iterative code decoding.