Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Machine Intelligence

Complex-encoded quantum convolutional neural networks

Zhipeng Xiao, Xiaoqing Tan, Daipengwei Bao, Rui Huang

Published Aug 8, 2025• 1 citation
Publisher
DOI
10.1007/s42484-025-00310-3

Related papers

Low-depth three-parameter quantum convolutional neural network for image classification

Jing Wang, Yong Zhang, 赵敏 Zhao Min

Quantum convolutional neural networks (QCNNs) typically consist of quantum encoding, convolution, and pooling layers. However, existing QCNNs for image classification still face two major limitations. Most encoding layers rely on single-parameter angle encoding, which limits their ability to represent complex image features. Many circuit architectures are relatively deep, increasing cir cuit complexity and noise accumulation and thus hindering implementation on noisy intermediate-scale quantum devices. To address these issues, this paper proposes a low-depth three-parameter encoding quantum convolutional neural network (LTP-QCNN) for image classification. The model employs a three parameter angle encoding layer that maps compressed image features onto the rotation angles of single-qubit gates. A first low-depth quantum convolutional layer is employed to extract local features, followed by a quantum pooling layer for quantum-state dimensionality reduction and information fusion. The pooled quantum states are then processed by a second quantum convolutional layer to extract discriminative features. Finally, the measured quantum feature vector is input into a classical classification layer to produce the final prediction. Simulation experiments were conducted on the Fashion-MNIST, MNIST, and KMNIST benchmark datasets. On Fashion-MNIST, LTP-QCNN achieved an accuracy of 99.85% on binary classification, while the accuracies for five-class and six class tasks reached 90.98% and 89.48%, respectively. The results demonstrate that LTP-QCNN achieves effective and stable image classification under limited quantum resources.

Indonesian Journal of Electrical Engineering and Computer Science•Sep 1, 2026•0 citations

Quantum-inspired complex convolutional neural networks

Shangshang Shi, Zhimin Wang, Guolong Cui +5 more

arXiv:2111.00392•Applied Intelligence•Apr 7, 2022•34 citations

Research on image classification using quantum convolutional neural networks based on multiple approaches

Yumin Dong, Xiaofeng Ni, Tonglei Sun +2 more

Abstract With the significant enhancement of quantum computing capabilities and their expanding applications in various fields, quantum image processing combined with quantum computing has become a key area of research in quantum computing, holding important theoretical value. In the face of the challenges posed by the digital information era, image classification technology demands higher standards from machine learning algorithms in terms of accuracy, computational speed, generalization capability, and complexity. This paper studies a series of quantum data encoding methods and parametric quantum circuit architectures, and proposes the application of Hybrid Hierarchical Encoding (HHE) and Hybrid Quantum Convolutional Neural Network (HQCNN). The new encoding method HHE integrates the benefits of angle encoding and enhances the hybrid amplitude encoding design to achieve optimal classification performance without compromising the depth of quantum circuits.HQCNN demonstrates outstanding classification performance and remarkable control over model complexity by leveraging the data processing capabilities of classical convolution and the complex computational power of quantum convolution. Experimental results show that HHE and HQCNN achieve better classification accuracy on the MNIST and Fashion-MNIST datasets compared to traditional classical CNN models, particularly when the number of parameters is significantly reduced.

Physica Scripta•Mar 18, 2025•2 citations

Quantum convolutional neural networks

Iris Cong, Soonwon Choi, Mikhail D. Lukin

arXiv:1810.03787•Nature Physics•Aug 26, 2019•1,523 citations

Multi-Class Quantum Convolutional Neural Networks Using Strongly Entangling Circuits

Infall Syafalni, Made Debby Almaeda Putri, Muchammad Dimas Sakti Widyatmaja +4 more

The rapid advancement of quantum computing technology has enabled new approaches to developing sophisticated machine learning models. In this paper, we present a multi-class Quantum Convolutional Neural Network (QCNN) architecture enhanced with strongly entangling circuits. The research targets the improvement of model's representation advantage and efficiency in solving classifications. The proposed method combines amplitude encoding with quantum convolutional and pooling layers or QCNN, augmented by strongly entangling layers to capture the data patterns. Experimental results show that our QCNN achieves higher classification accuracy with fewer parameters compared to traditional quantum models on the MNIST dataset. It highlights the potential of our method in complex multi-class classification.

International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)•Nov 4, 2025•0 citations

Quantum Convolution for Convolutional Neural Networks

Mustapha Bourahla

Information systems engineering and management•Jan 1, 2024•3 citations
Quantum convolutional neural networks (QCNNs) typically consist of quantum encoding, convolution, and pooling layers. However, existing QCNNs for image classification still face two major limitations. Most encoding layers rely on single-parameter angle encoding, which limits their ability to represent complex image features. Many circuit architectures are relatively deep, increasing cir cuit complexity and noise accumulation and thus hindering implementation on noisy intermediate-scale quantum devices. To address these issues, this paper proposes a low-depth three-parameter encoding quantum convolutional neural network (LTP-QCNN) for image classification. The model employs a three parameter angle encoding layer that maps compressed image features onto the rotation angles of single-qubit gates. A first low-depth quantum convolutional layer is employed to extract local features, followed by a quantum pooling layer for quantum-state dimensionality reduction and information fusion. The pooled quantum states are then processed by a second quantum convolutional layer to extract discriminative features. Finally, the measured quantum feature vector is input into a classical classification layer to produce the final prediction. Simulation experiments were conducted on the Fashion-MNIST, MNIST, and KMNIST benchmark datasets. On Fashion-MNIST, LTP-QCNN achieved an accuracy of 99.85% on binary classification, while the accuracies for five-class and six class tasks reached 90.98% and 89.48%, respectively. The results demonstrate that LTP-QCNN achieves effective and stable image classification under limited quantum resources.
Abstract With the significant enhancement of quantum computing capabilities and their expanding applications in various fields, quantum image processing combined with quantum computing has become a key area of research in quantum computing, holding important theoretical value. In the face of the challenges posed by the digital information era, image classification technology demands higher standards from machine learning algorithms in terms of accuracy, computational speed, generalization capability, and complexity. This paper studies a series of quantum data encoding methods and parametric quantum circuit architectures, and proposes the application of Hybrid Hierarchical Encoding (HHE) and Hybrid Quantum Convolutional Neural Network (HQCNN). The new encoding method HHE integrates the benefits of angle encoding and enhances the hybrid amplitude encoding design to achieve optimal classification performance without compromising the depth of quantum circuits.HQCNN demonstrates outstanding classification performance and remarkable control over model complexity by leveraging the data processing capabilities of classical convolution and the complex computational power of quantum convolution. Experimental results show that HHE and HQCNN achieve better classification accuracy on the MNIST and Fashion-MNIST datasets compared to traditional classical CNN models, particularly when the number of parameters is significantly reduced.
The rapid advancement of quantum computing technology has enabled new approaches to developing sophisticated machine learning models. In this paper, we present a multi-class Quantum Convolutional Neural Network (QCNN) architecture enhanced with strongly entangling circuits. The research targets the improvement of model's representation advantage and efficiency in solving classifications. The proposed method combines amplitude encoding with quantum convolutional and pooling layers or QCNN, augmented by strongly entangling layers to capture the data patterns. Experimental results show that our QCNN achieves higher classification accuracy with fewer parameters compared to traditional quantum models on the MNIST dataset. It highlights the potential of our method in complex multi-class classification.