Some implementations of NN-based medium blocklength channel codes, based on TurboAE
Y. Jiang, H. Kim, H. Asnani, S. Kannan, S. Oh, P. Viswanath, "Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels" Conference on Neural Information Processing Systems (NeurIPS), Vancouver, December 2019
and the repository https://github.com/yihanjiang/turboae; and https://github.com/Fritschek/ProductAE for productAE based on
Jamali, M.V., Saber, H., Hatami, H., & Bae, J.H. (2021). ProductAE: Toward Training Larger Channel Codes based on Neural Product Codes. ICC 2022 - IEEE International Conference on Communications
Added a few experimental additions to the TurboAE setup, including circular padding, layernorm, differentiable interleaver experiments.