Scientists at Singapore University of Technology and Design and others researchers in China propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process which is the most computational intensive part of CNN.
QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit’s depths, while retaining important features of classical CNN, such as nonlinearity and scalability. The team demonstrated the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with performance surpassing the CNN benchmark.