Machine learning approach for quantum non-Markovian noise classification

In this paper, machine learning and artificial neural network models are proposed for quantum noise classification in quantum dynamics affected by external noise. 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. As a result, we demonstrate the high efficacy of such tools in classifying noisy quantum dynamics using data sets collected from realizations of the quantum system dynamics. In addition, we 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. In doing this, neither measurements of quantum coherences nor sequences of control pulses may be necessarily required. Albeit the training of machine learning models is here performed a-priori on synthetic data, our approach is expected to find direct application in different experimental schemes, as e.g. the noise benchmarking of already available noisy intermediate-scale quantum devices.