arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.13843eess.SP
收藏

深度神经网络辅助的光学相干系统软解映射:回归与分类

Deep Neural Network-aided Soft-Demapping in Optical Coherent Systems: Regression versus Classification

Pedro J. Freire, Jaroslaw E. Prilepsky, Yevhenii Osadchuk, Sergei K. Turitsyn, Vahid Aref

摘要:

在这里,我们研究什么类型的预测建模,分类,或回归,使用神经网络(NN),更好地适合在相干光通信,其中传输信道是非线性和色散的软解映射的后处理的任务。这是第一次,我们提出了在机器学习环境中使用每种类型的预测任务可能存在的缺点,考虑到非线性相干光信道均衡/软解映射问题。我们研究了两种类型的均衡器的前馈和经常性神经网络的基础上,几种传输情况下,在线性和非线性制度的光信道。我们指出,即使从信息论的角度来看,交叉熵损失(分类)是我们的问题最合适的选择,基于交叉熵损失函数的NN模型可能会严重遭受学习问题。后者转化为这样一个事实,即基于回归的学习在提供更高的Q因子和可实现的信息速率方面通常更优越。总之,我们的经验证据表明,基于交叉熵的损失函数可能不一定是最合适的选择,在实际情况下,训练通信系统时,过拟合和消失的梯度相关的问题发挥作用。

英文摘要:

We examine here what type of predictive modelling, classification, or regression, using neural networks (NN), fits better the task of soft-demapping based post-processing in coherent optical communications, where the transmission channel is nonlinear and dispersive. For the first time, we present possible drawbacks in using each type of predictive task in a machine learning context, considering the nonlinear coherent optical channel equalization/soft-demapping problem. We study two types of equalizers based on the feed-forward and recurrent NNs, for several transmission scenarios, in linear and nonlinear regimes of the optical channel. We point out that even though from the information theory perspective the cross-entropy loss (classification) is the most suitable option for our problem, the NN models based on the cross-entropy loss function can severely suffer from learning problems. The latter translates into the fact that regression-based learning is typically superior in terms of delivering higher Q-factor and achievable information rates. In short, we show by empirical evidence that loss functions based on cross-entropy may not be necessarily the most suitable option for training communication systems in practical scenarios when overfitting- and vanishing gradients-related problems come into play.

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。

↑