Quantum Capsule Networks

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.

7 pages (main text) + 8 pages (supplementary information), 8 figures

References in corpus (29)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• The Quantum Internet
• Variational Quantum Algorithms
• Quantum computational advantage using photons
• Strong quantum computational advantage using a superconducting quantum processor
• Quantum random access memory
• Phase-Programmable Gaussian Boson Sampling Using Stimulated Squeezed Light
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Architectures for a quantum random access memory
• Quantum walks on a programmable two-dimensional 62-qubit superconducting processor
• Effect of barren plateaus on gradient-free optimization
• Machine learning meets quantum physics
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Circuit-Based Quantum Random Access Memory for Classical Data
• Entanglement Devised Barren Plateau Mitigation
• Barren plateaus preclude learning scramblers
• On barren plateaus and cost function locality in variational quantum algorithms
• Quantum federated learning through blind quantum computing
• Experimental quantum adversarial learning with programmable superconducting qubits
• Recent advances for quantum classifiers
• Representation Learning via Quantum Neural Tangent Kernels
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• Learning quantum data with the quantum Earth Mover's distance
• Quantum Wasserstein Generative Adversarial Networks
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Markovian Quantum Neuroevolution for Machine Learning
• ZhuSuan: A Library for Bayesian Deep Learning
• Distributed quantum inner product estimation
• Representation of binary classification trees with binary features by quantum circuits

Cited by in corpus (8)

• Harnessing Quantum Extreme Learning Machines for image classification
• Distributed quantum architecture search
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Enhancing Variational Quantum Circuit Training: An Improved Neural Network Approach for Barren Plateau Mitigation
• Quantum Active Learning
• Quantum approximated cloning-assisted density matrix exponentiation
• The Dual Role of Low-Weight Pauli Propagation: A Flawed Simulator but a Powerful Initializer for Variational Quantum Algorithms