In this paper, machine learning and artificial neural network models are proposed for quantum noise classification in stochastic quantum dynamics. For this purpose, we train and then validate support vector machine, multi-layer perceptron and recurrent neural network, models with different complexity and accuracy, to solve supervised binary classification problems. By exploiting the quantum random walk formalism, we demonstrate the high efficacy of such tools in classifying noisy quantum dynamics using data sets collected in a single realisation of the quantum system evolution. In addition, we also show that for a successful classification one just needs to measure, in a sequence of discrete time instants, the probabilities that the analysed quantum system is in one of the allowed positions or energy configurations, without any external driving. Thus, neither measurements of quantum coherences nor sequences of control pulses are required. Since in principle the training of the machine learning models can be performed a-priori on synthetic data, our approach is expected to find direct application in a vast number of experimental schemes and also for the noise benchmarking of the already available noisy intermediate-scale quantum devices.
翻译:在本文中,提出了机器学习和人工神经网络模型,用于在随机量子动态中进行量子噪音分类。为此,我们培训并验证支持矢量机、多层感应器和经常神经网络的概率,这些模型具有不同的复杂性和准确性,以解决受监督的二进制分类问题。通过利用量子随机行走形式主义,我们展示了这些工具在利用量子系统演变单一实现中收集的数据集对噪音量子动态进行分类方面的高效力。此外,我们还表明,为了成功地进行分类,需要在一个离散时间瞬间序列中测量分析的量子系统在允许的位置或能量配置中的概率,而没有任何外部驱动。因此,既不需要测量量子一致性,也不需要控制脉冲的序列。由于原则上可以对机器学习模型进行关于合成数据的优先培训,因此我们的方法可望在大量实验计划中找到直接应用,同时也需要为已有的噪声中等量量器装置的噪音基准进行测量。