For One-Shot Decoding: Self-supervised Deep Learning-Based Polar Decoder

• URL: http://arxiv.org/abs/2307.08004v2
• Date: Sun, 30 Jul 2023 04:26:55 GMT
• Title: For One-Shot Decoding: Self-supervised Deep Learning-Based Polar Decoder
• Authors: Huiying Song, Yihao Luo, Yuma Fukuzawa
• Abstract summary: We propose a self-supervised deep learning-based decoding scheme that enables one-shot decoding of polar codes. In the proposed scheme, rather than using the information bit vectors as labels for training the neural network (NN), the NN is trained to function as a bounded distance decoder.
• Score: 1.4964546566293881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a self-supervised deep learning-based decoding scheme that enables one-shot decoding of polar codes. In the proposed scheme, rather than using the information bit vectors as labels for training the neural network (NN) through supervised learning as the conventional scheme did, the NN is trained to function as a bounded distance decoder by leveraging the generator matrix of polar codes through self-supervised learning. This approach eliminates the reliance on predefined labels, empowering the potential to train directly on the actual data within communication systems and thereby enhancing the applicability. Furthermore, computer simulations demonstrate that (i) the bit error rate (BER) and block error rate (BLER) performances of the proposed scheme can approach those of the maximum a posteriori (MAP) decoder for very short packets and (ii) the proposed NN decoder (NND) exhibits much superior generalization ability compared to the conventional one.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.