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:2401.07405 · Quantum Machine Intelligence

Effective detection of quantum discord by using convolutional neural networks

Narjes Taghadomi, A. Mani, Ali Fahim, Ali Bakouei

Published Mar 12, 2025• 5 citations
arXivHTMLPDF
DOI
10.1007/s42484-025-00267-3

Related papers

Quantum splitting convolutional neural network-based distributed quantum disease detection model

Yangyang Li, Zhengya Qi, Yuelin Li +3 more

Neurocomputing•Sep 4, 2025•7 citations

Study on estimating quantum discord by neural network with prior knowledge

Yong-Lei Liu, An Min Wang, Yi Sun +2 more

arXiv:1905.10782•Quantum Information Processing•Oct 10, 2019•4 citations

Multi-Path Parallel Quantum Convolutional Neural Network

Han Qi, Xintong Huo, Abdullah Gani

Quantum Convolutional Neural Networks (QCNN) migrate the convolution and pooling concepts of classical Convolutional Neural Networks (CNN) to variational quantum circuits, showing potential on Noisy Intermediate-Scale Quantum (NISQ) devices. However, traditional QCNN adopts a single-depth circuit structure, which has limitations in multi-scale feature extraction, and is prone to the barren plateau phenomenon during training, making it difficult to adapt to high-dimensional real-world scenarios such as network intrusion detection. This paper proposes a QCNN architecture based on a multi-path parallel structure. For the network intrusion detection task, it draws on the Inception module to construct three parallel quantum convolution paths: shallow, medium, and deep, achieving hierarchical extraction of multi-scale features; residual connections are introduced to preserve encoded state information and provide gradient shortcuts; a hybrid optimization strategy combining classical Adam and Quantum Natural Gradient (QNG) is adopted to adapt to the heterogeneous parameter space. Experimental validation shows that, on the UNSW-NB15 network intrusion detection dataset, the proposed Multi-Path Parallel Quantum Convolutional Neural Network (MP-QCNN) improves detection accuracy by 3% compared to traditional single-path QCNN and effectively mitigates the barren plateau phenomenon. This design strictly maintains NISQ depth constraints and quantum parallelism advantages, providing an efficient and stable feature extraction framework for high-dimensional tasks such as network intrusion detection.

International Conference on Multi-scale Artificial Intelligence (MAI)•Apr 24, 2026•0 citations

Applying Gaussian quantum discord to quantum key distribution

Xiaolong Su

arXiv:1310.4253•Chinese Science Bulletin•Feb 24, 2014•59 citations

Utilizing Quantum Variational Circuits to Perform Quantum Convolutions in Hybrid "Quanvolutional" Neural Networks for Skin Cancer Detection

Idhant Gode, Haiyan Wang, David Liang

Cancer is one of the leading causes of death worldwide. Mutations in humans can alter oncogenes or tumor suppressor genes, leading to uncontrolled cell growth. The most common form of cancer is skin cancer which if caught early, is much easier to treat, highlighting the importance of a sophisticated skin cancer detection system. In this study, we propose a novel method to detect skin cancer early, utilizing quantum variational circuits to perform a quantum convolution as a pre-processing step on image data for classical Convolutional Neural Networks (CNN) to create a hybrid "Quanvolutional" Neural Network. Utilizing a dataset of over 8,100 images which included images of other skin conditions including Herpes Simplex, Burns, Xerosis, folliculitis, and more, our model obtained a validation accuracy of 99.30% for the classification of Skin Cancer. This performance surpasses that of similar, purely classical CNNs, despite the presence of noise from other skin conditions. Our study not only demonstrates significant potential for skin cancer detection, but also the efficiency and effectiveness of quantum pre-processing layers in hybrid Quanvolutional Neural Networks. Future work can utilize our Quantum Machine Learning methods, leading to further breakthroughs within the medical field and quantum computing as a whole.

International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)•Nov 22, 2024•0 citations

Design of an Improved Quantum Neural Network with Edge Detection Procedure Using Convolutional Neural Networks – A Machine Learning Model

K S Vairavel, S.Sangeetha, Ahmad Al-Qerem +3 more

Quantum Neural Networks (QNN) merge quantum computing with neural networks, leveraging qubits and quantum gates for enhanced feature representation and parallel computation through superposition and entanglement. A novel approach is presented in this work, an Intelligent Quantum Edge-based Convolutional Neural Network (IQECNN) model combining Deep Learning (DL) and Quantum Computing (QC) for image analysis. Initially, a classical Convolutional Neural Network (CNN) is used to extract features through convolution and pooling. These features are then prepared for the quantum processor, where a QNN layer applies unitary quantum gates to produce classification results. To enhance edge detection, a quantum-inspired multilevel thresholding method is integrated with Particle Swarm Optimisation (PSO) for precise boundary localisation. The performance analysis has an accuracy of 99%, a loss of epochs of 3 (5.0), a confusion matrix of train 47 FP and 28 FN of and test data of 187 TN and 245 TP, and a ROC curve of train of 0.99 and test data of 0.96 calculations.

International Conference on Recent Innovation in Science Engineering and Technology (ICRISET)•Aug 1, 2026•0 citations
Quantum Convolutional Neural Networks (QCNN) migrate the convolution and pooling concepts of classical Convolutional Neural Networks (CNN) to variational quantum circuits, showing potential on Noisy Intermediate-Scale Quantum (NISQ) devices. However, traditional QCNN adopts a single-depth circuit structure, which has limitations in multi-scale feature extraction, and is prone to the barren plateau phenomenon during training, making it difficult to adapt to high-dimensional real-world scenarios such as network intrusion detection. This paper proposes a QCNN architecture based on a multi-path parallel structure. For the network intrusion detection task, it draws on the Inception module to construct three parallel quantum convolution paths: shallow, medium, and deep, achieving hierarchical extraction of multi-scale features; residual connections are introduced to preserve encoded state information and provide gradient shortcuts; a hybrid optimization strategy combining classical Adam and Quantum Natural Gradient (QNG) is adopted to adapt to the heterogeneous parameter space. Experimental validation shows that, on the UNSW-NB15 network intrusion detection dataset, the proposed Multi-Path Parallel Quantum Convolutional Neural Network (MP-QCNN) improves detection accuracy by 3% compared to traditional single-path QCNN and effectively mitigates the barren plateau phenomenon. This design strictly maintains NISQ depth constraints and quantum parallelism advantages, providing an efficient and stable feature extraction framework for high-dimensional tasks such as network intrusion detection.
Cancer is one of the leading causes of death worldwide. Mutations in humans can alter oncogenes or tumor suppressor genes, leading to uncontrolled cell growth. The most common form of cancer is skin cancer which if caught early, is much easier to treat, highlighting the importance of a sophisticated skin cancer detection system. In this study, we propose a novel method to detect skin cancer early, utilizing quantum variational circuits to perform a quantum convolution as a pre-processing step on image data for classical Convolutional Neural Networks (CNN) to create a hybrid "Quanvolutional" Neural Network. Utilizing a dataset of over 8,100 images which included images of other skin conditions including Herpes Simplex, Burns, Xerosis, folliculitis, and more, our model obtained a validation accuracy of 99.30% for the classification of Skin Cancer. This performance surpasses that of similar, purely classical CNNs, despite the presence of noise from other skin conditions. Our study not only demonstrates significant potential for skin cancer detection, but also the efficiency and effectiveness of quantum pre-processing layers in hybrid Quanvolutional Neural Networks. Future work can utilize our Quantum Machine Learning methods, leading to further breakthroughs within the medical field and quantum computing as a whole.
Quantum Neural Networks (QNN) merge quantum computing with neural networks, leveraging qubits and quantum gates for enhanced feature representation and parallel computation through superposition and entanglement. A novel approach is presented in this work, an Intelligent Quantum Edge-based Convolutional Neural Network (IQECNN) model combining Deep Learning (DL) and Quantum Computing (QC) for image analysis. Initially, a classical Convolutional Neural Network (CNN) is used to extract features through convolution and pooling. These features are then prepared for the quantum processor, where a QNN layer applies unitary quantum gates to produce classification results. To enhance edge detection, a quantum-inspired multilevel thresholding method is integrated with Particle Swarm Optimisation (PSO) for precise boundary localisation. The performance analysis has an accuracy of 99%, a loss of epochs of 3 (5.0), a confusion matrix of train 47 FP and 28 FN of and test data of 187 TN and 245 TP, and a ROC curve of train of 0.99 and test data of 0.96 calculations.