Quantum Capsule Networks

TL;DR

This paper introduces a quantum capsule network (QCapsNet) with an efficient routing algorithm, demonstrating improved classification accuracy and potential explainability in quantum machine learning tasks through extensive simulations.

Contribution

The paper presents the first quantum capsule network with a novel routing algorithm, showing enhanced performance and interpretability over traditional quantum classifiers.

Findings

QCapsNet outperforms conventional quantum classifiers in accuracy.

A specific subspace of the output capsule correlates with human-understandable features.

The network demonstrates potential for explainable quantum artificial intelligence.

Abstract

Capsule networks, which incorporate the paradigms of connectionism and symbolism, have brought fresh insights into artificial intelligence. The capsule, as the building block of capsule networks, 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 quantum capsule networks in quantum machine learning, which may provide a valuable guide towards explainable quantum artificial intelligence.