Lorenz, Jeanette MiriamJeanette MiriamLorenz2022-05-302022-05-302022-05-03https://publica.fraunhofer.de/handle/publica/418039To achieve practical quantum advantage, multiple ingredients are required: identification of suitable application fields, a software stack, e.g. providing a fast iteration between quantum and classical computers and an additional abstraction layer for users. Within this talk, a quantum-classical convolutional neural network for radiological classification tasks is presented, that promises an quantum advantage in the presence of little training data. Furthermore, the project QuaST tries to enable an additional abstraction layer to make the quantum-computing-assisted solution of optimization problems easily available for industrial end users in a robust way.ennear-term quantum computingNISQ algorithmQuantum Convolutional Neural NetworksQuantum Classical Convolutional Neural NetworksQCCNNpresentation