Quantum capsule networks

Capsule networks (CapsNets), which incorporate the paradigms of connectionism and symbolism, have brought fresh insights into artificial intelligence (AI). The capsule, as the building block of CapsNets, is a group of neurons represented by a vector to encode different features of an entity. The information is extracted hierarchically through capsule layers via routing algorithms. Here, we introduce a quantum capsule network (dubbed QCapsNet) together with an efficient quantum dynamic routing algorithm. To benchmark the performance of the QCapsNet, we carry out extensive numerical simulations on the classification of handwritten digits and symmetry-protected topological phases, and show that the QCapsNet can achieve an enhanced accuracy and outperform conventional quantum classifiers evidently. We further unpack the output capsule state and find that a particular subspace may correspond to a human-understandable feature of the input data, which indicates the potential explainability of such networks. Our work reveals an intriguing prospect of QCapsNets in quantum machine learning, which may provide a valuable guide towards explainable quantum AI.

Automated summary

The researchers introduce a quantum capsule network (QCapsNet) with an efficient quantum dynamic routing algorithm, which shows enhanced performance and potential explainability compared to conventional quantum classifiers. This work has important implications for quantum machine learning and explainable quantum AI.