Opt Express. 2021 Apr 12;29(8):11591-11604. doi: 10.1364/OE.419609.
Nonlinear Fourier transform, as a technique that has a great potential to overcome the capacity limit in fibre optical communication system, faces speed and accuracy bottlenecks in practice. Machine learning using convolutional neural networks shows great potential in NFT-based applications. We have developed a convolutional neural network for decoding information in NFT-based communication and numerically demonstrated its performance in comparison to a fast NFT algorithm. The comparison indicates the potential of conventional neural network to replace NFT calculations for decoding of information.
非线性傅里叶变换作为一种有很大潜力克服光纤通信系统容量限制的技术，在实际应用中面临速度和精度的瓶颈。基于卷积神经网络的机器学习在 NFT 应用中显示出巨大的潜力。我们开发了一种用于解码 NFT 通信中信息的卷积神经网络，并数值比较了其性能与快速 NFT 算法。比较结果表明，传统神经网络有可能取代 NFT 计算，用于信息的解码。
