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

International Conference on Photonics, Optics and Laser Technology

Elements of Hybrid Opto-superconducting Convolutional Neural Networks

Andrey E. Schegolev, N. V. Klenov, Maxim V Tereshonok, S. S. Adjemov

Published Jan 1, 2020• 1 citation
Publisher
DOI
10.5220/0009100101350139

Related papers

Superconducting optoelectronic networks I: general principles

Jeffrey M. Shainline, Sonia Mary Buckley, Adam N. McCaughan +3 more

Physical Review Applied•Apr 6, 2018•0 citations

Stabilization of Image Classification Accuracy in Hybrid Quantum-Classical Convolutional Neural Network with Ensemble Learning

Hayatou Oumarou, Yahdi Siradj, Randi Rizal +1 more

Stabilization of Image Classification Accuracy in Hybrid Quantum-Classical Convolutional Neural Network Model with Ensemble Learning. Image classification plays a significant role in various technological applications, such as object recognition, autonomous vehicles, and medical image processing. Higher accuracy in image classification implies better capabilities in recognizing and understanding visual information. To enhance image classification accuracy, a Hybrid Quantum-Classical Convolutional Neural Network (HQ-CNN) model is developed by integrating quantum and classical computing elements with ensemble learning techniques. Compared to conventional neural networks, HQ-CNN enriches feature mapping in image classification predictions. The research results with HQ-CNN using ensemble learning demonstrate impressive and stable accuracy, with the lowest deviation being 1.1037.

Innovation in Research of Informatics (INNOVATICS)•Mar 30, 2024•0 citations

Superconducting artificial neural networks and quantum circuits

Anatolie Sidorenko

Beilstein Journal of Nanotechnology•Jun 8, 2026•0 citations

Quantum Dilated Convolutional Neural Networks

Yixiong Chen

In recent years, with rapid progress in the development of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a family of hybrid quantum-classical neural networks, consisting of classical and quantum elements, has been massively explored for the purpose of improving the performance of classical neural networks. In this paper, we propose a novel hybrid quantum-classical algorithm called quantum dilated convolutional neural networks (QDCNNs). Our method extends the concept of dilated convolution, which has been widely applied in modern deep learning algorithms, to the context of hybrid neural networks. The proposed QDCNNs are able to capture larger context during the quantum convolution process while reducing the computational cost. We perform empirical experiments on MNIST and Fashion-MNIST datasets for the task of image recognition and demonstrate that QDCNN models generally enjoy better performances in terms of both accuracy and computation efficiency compared to existing quantum convolutional neural networks (QCNNs).

IEEE Access•Jan 1, 2022•38 citations

QDCNN: Quantum Dilated Convolutional Neural Network

Yixiong Chen

In recent years, with rapid progress in the development of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a family of hybrid quantum-classical neural networks, consisting of classical and quantum elements, has been massively explored for the purpose of improving the performance of classical neural networks. In this paper, we propose a novel hybrid quantum-classical algorithm called quantum dilated convolutional neural networks (QDCNNs). Our method extends the concept of dilated convolution, which has been widely applied in modern deep learning algorithms, to the context of hybrid neural networks. The proposed QDCNNs are able to capture larger context during the quantum convolution process while reducing the computational cost. We perform empirical experiments on MNIST and Fashion-MNIST datasets for the task of image recognition and demonstrate that QDCNN models generally enjoy better performances in terms of both accuracy and computation efficiency compared to existing quantum convolutional neural networks (QCNNs).

arXiv:2110.15667•Oct 29, 2021•6 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
Stabilization of Image Classification Accuracy in Hybrid Quantum-Classical Convolutional Neural Network Model with Ensemble Learning. Image classification plays a significant role in various technological applications, such as object recognition, autonomous vehicles, and medical image processing. Higher accuracy in image classification implies better capabilities in recognizing and understanding visual information. To enhance image classification accuracy, a Hybrid Quantum-Classical Convolutional Neural Network (HQ-CNN) model is developed by integrating quantum and classical computing elements with ensemble learning techniques. Compared to conventional neural networks, HQ-CNN enriches feature mapping in image classification predictions. The research results with HQ-CNN using ensemble learning demonstrate impressive and stable accuracy, with the lowest deviation being 1.1037.
In recent years, with rapid progress in the development of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a family of hybrid quantum-classical neural networks, consisting of classical and quantum elements, has been massively explored for the purpose of improving the performance of classical neural networks. In this paper, we propose a novel hybrid quantum-classical algorithm called quantum dilated convolutional neural networks (QDCNNs). Our method extends the concept of dilated convolution, which has been widely applied in modern deep learning algorithms, to the context of hybrid neural networks. The proposed QDCNNs are able to capture larger context during the quantum convolution process while reducing the computational cost. We perform empirical experiments on MNIST and Fashion-MNIST datasets for the task of image recognition and demonstrate that QDCNN models generally enjoy better performances in terms of both accuracy and computation efficiency compared to existing quantum convolutional neural networks (QCNNs).
In recent years, with rapid progress in the development of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a family of hybrid quantum-classical neural networks, consisting of classical and quantum elements, has been massively explored for the purpose of improving the performance of classical neural networks. In this paper, we propose a novel hybrid quantum-classical algorithm called quantum dilated convolutional neural networks (QDCNNs). Our method extends the concept of dilated convolution, which has been widely applied in modern deep learning algorithms, to the context of hybrid neural networks. The proposed QDCNNs are able to capture larger context during the quantum convolution process while reducing the computational cost. We perform empirical experiments on MNIST and Fashion-MNIST datasets for the task of image recognition and demonstrate that QDCNN models generally enjoy better performances in terms of both accuracy and computation efficiency compared to existing quantum convolutional neural networks (QCNNs).