Hybrid Quantum Network for classification of finance and MNIST data

In the ongoing era of noisy intermediate scaled quantum computers, one of the possible applications to search for an advantage of quantum computing is machine learning. Here we report about an approach, where a hybrid quantumclassical network is applied to classify non-trivial datasets (finance and MNIST data). In comparison to a pure classical network, we find an advantage when looking at several performance measures. However, as in classical machine learning problems around overfitting the dataset arise. Therefore, we outline the path to future research, which has to be done in the field of (hybrid) quantum networks.