Quantum Capsule Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 102 references that are in the map. First posted on arXiv 5 Jan 2022.
Builds on
27 of 102 references.
References · 27
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Dynamic Routing Between Capsulescited by 689
- 2020Variational Quantum Algorithmscited by 687
- 2018Barren plateaus in quantum neural network training landscapescited by 624
- 2019Parameterized quantum circuits as machine learning modelscited by 330
- 2020Noise-Induced Barren Plateaus in Variational Quantum Algorithmscited by 192
- 2019Efficient Learning for Deep Quantum Neural Networkscited by 160
- 2018Quantum generative adversarial networkscited by 128
- 2020Absence of Barren Plateaus in Quantum Convolutional Neural Networkscited by 124
- 2020Entanglement Induced Barren Plateauscited by 101
- 2020Effect of barren plateaus on gradient-free optimizationcited by 79
- 2019Quantum Adversarial Machine Learningcited by 64
15 more
- 2020Trainability of Dissipative Perceptron-Based Quantum Neural Networkscited by 56
- 2021Equivalence of quantum barren plateaus to cost concentration and narrow gorgescited by 53
- 2021Quantum federated learning through blind quantum computingcited by 44
- 2021Representation Learning via Quantum Neural Tangent Kernelscited by 40
- 2020On barren plateaus and cost function locality in variational quantum algorithmscited by 36
- 2021Recent advances for quantum classifierscited by 35
- 2018Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptionscited by 34
- 2019Quantum Wasserstein Generative Adversarial Networkscited by 33
- 2021Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculuscited by 30
- 2021Learning quantum data with the quantum Earth Mover's distancecited by 13
- 2017ZhuSuan: A Library for Bayesian Deep Learningcited by 8
- 2019Quantum Expectation-Maximization for Gaussian Mixture Modelscited by 8
- 2021Representation of binary classification trees with binary features by quantum circuitscited by 7
- 2018Improved Explainability of Capsule Networks: Relevance Path by Agreementcited by 6
- 2019Quantum Expectation-Maximization Algorithmcited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.