arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1902.08394cs.ITcs.LGmath.IT
收藏

利用LSTM网络学习极化码的翻转逐次抵消译码

Learning to Flip Successive Cancellation Decoding of Polar Codes with LSTM Networks

Huawei Technologies Co., Ltd.(华为技术有限公司)

Xianbin Wang, Huazi Zhang, Rong Li, Lingchen Huang, Shengchen Dai, Yourui Huangfu, Jun Wang

摘要:

极化码的连续消除(SC)翻转解码的关键是准确地识别第一错误比特。由于缺乏分析解,最佳翻转策略被认为很困难。或者,我们提出了一种深度学习辅助的SC翻转算法。具体地,在每次SC解码尝试之前,利用长短期记忆(LSTM)网络来(i)定位第一错误比特,或者(ii)撤销先前的“错误”翻转。在每次SC尝试中,利用在先前SC尝试中导出的对数似然比(LLR)的序列来决定采取哪个动作。因此,提出了LSTM网络的两阶段训练方法,即,学会在第一阶段定位第一个错误位,然后在第二阶段撤销“错误”翻转。仿真结果表明,该方法能够更准确地识别错误比特,并取得了更好的性能比国家的最先进的SC翻转算法。

英文摘要:

The key to successive cancellation (SC) flip decoding of polar codes is to accurately identify the first error bit. The optimal flipping strategy is considered difficult due to lack of an analytical solution. Alternatively, we propose a deep learning aided SC flip algorithm. Specifically, before each SC decoding attempt, a long short-term memory (LSTM) network is exploited to either (i) locate the first error bit, or (ii) undo a previous `wrong' flip. In each SC attempt, the sequence of log likelihood ratios (LLRs) derived in the previous SC attempt is exploited to decide which action to take. Accordingly, a two-stage training method of the LSTM network is proposed, i.e., learn to locate first error bits in the first stage, and then to undo `wrong' flips in the second stage. Simulation results show that the proposed approach identifies error bits more accurately and achieves better performance than the state-of-the-art SC flip algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑