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

arXiv:2404.12741

Multi-Class Quantum Convolutional Neural Networks

Marco Mordacci, Davide Ferrari, Michele Amoretti

Published Jun 3, 2024• 9 citations
arXivHTMLPDF

Abstract

Classification is particularly relevant to Information Retrieval, as it is used in various subtasks of the search pipeline. In this work, we propose a quantum convolutional neural network (QCNN) for multi-class classification of classical data. The model is implemented using PennyLane. The optimization process is conducted by minimizing the cross-entropy loss through parameterized quantum circuit optimization. The QCNN is tested on the MNIST dataset with 4, 6, 8 and 10 classes. The results show that with 4 classes, the performance is slightly lower compared to the classical CNN, while with a higher number of classes, the QCNN outperforms the classical neural network.

DOI
10.1145/3660318.3660326

Related papers

Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning

Denis Bokhan, Alena S. Mastiukova, Aleksey S. Boev +2 more

Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that the accuracy of our solution is similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our findings will provide a new step toward the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.

arXiv:2203.15368•Frontiers in Physics•Nov 23, 2022•81 citations

Quantum Convolutional Neural Network Architecture for Multi-Class Classification

Samarth Kashyap, Shayan Srinivasa Garani

We propose quantum circuit architectures for convolutional neural networks based on generalized 3-qubit and 2-qubit quantum gates for the multiclass classification problem. The quantum architecture is equivalent to a classical convolutional neural network with fully connected layers and densely connected layers. The quantum circuit parameters are optimized by minimizing the cross-entropy loss function. We validate the classification performance over several model configurations on the MNIST, Fashion-MNIST and Kuzushiji-MNIST datasets. Our proposed architecture shows classification accuracies that are comparable to classical CNNs with a similar number of parameters. In addition to this, we find that circuit depth is greatly decreased by a logarithmic factor compared to classical CNNs. We study the performance and complexity tradeoffs over several model configurations within the proposed quantum CNN architecture.

International Joint Conference on Neural Networks (IJCNN)•Jun 18, 2023•7 citations

Architectural Design of Quantum Convolutional Neural Network for Multi-Class Image Classification

Shichen Song, Kehan Chen

This study proposes a quantum convolutional neural network (QCNN) designed for image multi-classification tasks. To enhance feature extraction, the quantum convolutional employs singular value decomposition (SVD) to construct custom quantum gates. Quantum fully connected layers are built based on the swap test, which improves both generalization and classification performance. The QCNN is trained and tested on the PennyLane quantum computing framework. It achieves a test accuracy of$\mathbf{9 4. 0 7 \%}$on a four-class classification task using the MNIST dataset. To evaluate its practicality, simulation experiments are conducted under various types of quantum noise. The results show that the QCNN remains robust against noise, demonstrating strong potential for practical quantum environments.

International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA)•Jun 20, 2025•1 citation

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

HYBRID CLASSICAL–QUANTUM CONVOLUTIONAL NEURAL NETWORK USING PENNYLANE FOR OVERHEAD-MNIST IMAGE CLASSIFICATION

Quantum machine learning has emerged as a promising approach for enhancing classical deep learning models by leveraging quantum computational properties.In this work, a hybrid Quantum-Classical Convolutional Neural Network (QC-CNN) is proposed for overhead image classification using the Overhead-MNIST dataset.The model integrates a classical Convolutional Neural Network (CNN) for spatial feature extraction with a parameterized quantum circuit that performs quantum feature transformation through angle embedding and strongly entangling layers.Initially, input images are preprocessed and resized, after which the CNN extracts high-level feature representations.These features are then encoded into quantum states and processed through a variational quantum layer to capture complex feature correlations using quantum operations.The output of the quantum circuit is passed to fully connected layers for final classification.The hybrid architecture is trained end-to-end using a gradient-based optimization approach.Experimental results demonstrate that the proposed QC-CNN model achieves high classification accuracy on the selected classes of the Overhead-MNIST dataset while maintaining stable training behavior.The results indicate that integrating quantum circuits with classical deep learning frameworks can improve feature representation and provide a potential pathway toward future quantum-enhanced intelligent vision systems.

International Research Journal of Modernization in Engineering Technology and Science•Mar 16, 2026•0 citations

Image Classification using Quantum Convolutional Neural Network (QCNN)

R. Sivaranjani, Bandaru Shanmukha Priya, Omprakash Gurrapu +3 more

Convolutional Neural Networks (CNNs) are extensively utilized for image classification due to their ability to exploit data correlations effectively. However, traditional CNNs encounter several challenges, including limitations in accuracy improvement, computational efficiency, explain ability, and generalization. As data dimensionality or model complexity increases, CNNs often become more difficult to train efficiently, leading to slower processing times. To overcome these challenges, Quantum Convolutional Neural Networks (QCNNs) offer a promising quantum-based approach to enhance existing models, particularly by improving training efficiency and reducing processing times. This paper provides a comparative analysis of classical CNNs and a novel quantum circuit architecture tailored for image-based tasks. The analysis emphasizes the adaptability and potential of quantum circuits to enhance feature extraction, recognition accuracy, and processing efficiency.We applied various QCNN architectures to the Chinese-MNIST dataset and compared their performance with traditional CNN models. Although QCNNs achieved slightly lower accuracy, they demonstrated significantly greater stability. These findings high- light QCNNs’ potential to overcome the computational limitations of conventional deep learning, offering a promising pathway for quantum-enhanced solutions in computer vision. Future work will focus on refining quantum circuit designs, developing hybrid quantum-classical models, and extending QCNN applications to larger and more diverse datasets.

International Conference on Metaverse and Current Trends in Computing (ICMCTC)•Apr 10, 2025•2 citations
Classification is particularly relevant to Information Retrieval, as it is used in various subtasks of the search pipeline. In this work, we propose a quantum convolutional neural network (QCNN) for multi-class classification of classical data. The model is implemented using PennyLane. The optimization process is conducted by minimizing the cross-entropy loss through parameterized quantum circuit optimization. The QCNN is tested on the MNIST dataset with 4, 6, 8 and 10 classes. The results show that with 4 classes, the performance is slightly lower compared to the classical CNN, while with a higher number of classes, the QCNN outperforms the classical neural network.
Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that the accuracy of our solution is similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our findings will provide a new step toward the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.
We propose quantum circuit architectures for convolutional neural networks based on generalized 3-qubit and 2-qubit quantum gates for the multiclass classification problem. The quantum architecture is equivalent to a classical convolutional neural network with fully connected layers and densely connected layers. The quantum circuit parameters are optimized by minimizing the cross-entropy loss function. We validate the classification performance over several model configurations on the MNIST, Fashion-MNIST and Kuzushiji-MNIST datasets. Our proposed architecture shows classification accuracies that are comparable to classical CNNs with a similar number of parameters. In addition to this, we find that circuit depth is greatly decreased by a logarithmic factor compared to classical CNNs. We study the performance and complexity tradeoffs over several model configurations within the proposed quantum CNN architecture.
This study proposes a quantum convolutional neural network (QCNN) designed for image multi-classification tasks. To enhance feature extraction, the quantum convolutional employs singular value decomposition (SVD) to construct custom quantum gates. Quantum fully connected layers are built based on the swap test, which improves both generalization and classification performance. The QCNN is trained and tested on the PennyLane quantum computing framework. It achieves a test accuracy of94.07%\mathbf{9 4. 0 7 \%}94.07%on a four-class classification task using the MNIST dataset. To evaluate its practicality, simulation experiments are conducted under various types of quantum noise. The results show that the QCNN remains robust against noise, demonstrating strong potential for practical quantum environments.
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.
Quantum machine learning has emerged as a promising approach for enhancing classical deep learning models by leveraging quantum computational properties.In this work, a hybrid Quantum-Classical Convolutional Neural Network (QC-CNN) is proposed for overhead image classification using the Overhead-MNIST dataset.The model integrates a classical Convolutional Neural Network (CNN) for spatial feature extraction with a parameterized quantum circuit that performs quantum feature transformation through angle embedding and strongly entangling layers.Initially, input images are preprocessed and resized, after which the CNN extracts high-level feature representations.These features are then encoded into quantum states and processed through a variational quantum layer to capture complex feature correlations using quantum operations.The output of the quantum circuit is passed to fully connected layers for final classification.The hybrid architecture is trained end-to-end using a gradient-based optimization approach.Experimental results demonstrate that the proposed QC-CNN model achieves high classification accuracy on the selected classes of the Overhead-MNIST dataset while maintaining stable training behavior.The results indicate that integrating quantum circuits with classical deep learning frameworks can improve feature representation and provide a potential pathway toward future quantum-enhanced intelligent vision systems.
Convolutional Neural Networks (CNNs) are extensively utilized for image classification due to their ability to exploit data correlations effectively. However, traditional CNNs encounter several challenges, including limitations in accuracy improvement, computational efficiency, explain ability, and generalization. As data dimensionality or model complexity increases, CNNs often become more difficult to train efficiently, leading to slower processing times. To overcome these challenges, Quantum Convolutional Neural Networks (QCNNs) offer a promising quantum-based approach to enhance existing models, particularly by improving training efficiency and reducing processing times. This paper provides a comparative analysis of classical CNNs and a novel quantum circuit architecture tailored for image-based tasks. The analysis emphasizes the adaptability and potential of quantum circuits to enhance feature extraction, recognition accuracy, and processing efficiency.We applied various QCNN architectures to the Chinese-MNIST dataset and compared their performance with traditional CNN models. Although QCNNs achieved slightly lower accuracy, they demonstrated significantly greater stability. These findings high- light QCNNs’ potential to overcome the computational limitations of conventional deep learning, offering a promising pathway for quantum-enhanced solutions in computer vision. Future work will focus on refining quantum circuit designs, developing hybrid quantum-classical models, and extending QCNN applications to larger and more diverse datasets.