Abstract Deep learning achieves unprecedented success involves many fields, whereas the high requirement of memory and time efficiency tolerance have been the intractable challenges for a long time. On the other hand, quantum computing shows its superiorities in some computation problems owing to its intrinsic properties of superposition and entanglement, which may provide a new path to settle these issues. In this paper, a quantum deep convolutional neural network (QDCNN) model based on the quantum parameterized circuit for image recognition is investigated. In analogy to the classical deep convolutional neural network (DCNN), the architecture that a sequence of quantum convolutional layers followed by a quantum classified layer is illustrated. Inspired by the variational quantum algorithms, a quantum–classical hybrid training scheme is demonstrated for the parameter updating in the QDCNN. The network complexity analysis indicates the proposed model provides the exponential acceleration comparing with the classical counterpart. Furthermore, the MNIST and GTSRB datasets are employed to numerical simulation and the quantitative experimental results verify the feasibility and validity.
Abstract Deep learning achieves unprecedented success involves many fields, whereas the high requirement of memory and time efficiency tolerance have been the intractable challenges for a long time. On the other hand, quantum computing shows its superiorities in some computation problems owing to its intrinsic properties of superposition and entanglement, which may provide a new path to settle these issues. In this paper, a quantum deep convolutional neural network (QDCNN) model based on the quantum parameterized circuit for image recognition is investigated. In analogy to the classical deep convolutional neural network (DCNN), the architecture that a sequence of quantum convolutional layers followed by a quantum classified layer is illustrated. Inspired by the variational quantum algorithms, a quantum–classical hybrid training scheme is demonstrated for the parameter updating in the QDCNN. The network complexity analysis indicates the proposed model provides the exponential acceleration comparing with the classical counterpart. Furthermore, the MNIST and GTSRB datasets are employed to numerical simulation and the quantitative experimental results verify the feasibility and validity.
Quantum computing is rapidly reshaping the landscape of image recognition by offering enhanced computational capabilities. Classical deep learning architectures such as Convolutional Neural Networks (CNNs) struggle with scalability and efficiency when handling high-dimensional quantum image data. Quantum-enhanced Dilated Convolutional Networks (Q-DCNs) have emerged as a novel solution to this problem. Traditional CNNs, even with dilation, are computationally intensive on large-scale or entangled quantum image datasets. These models fail to exploit quantum parallelism and often suffer from vanishing gradients and redundant parameterization. There is a need for an optimized hybrid quantum-classical model that combines the generalization capacity of dilation with the processing power of quantum circuits. We propose a Quantum-Enhanced Dilated Convolutional Network (Q-DCN), wherein dilated convolutional layers are hybridized with quantum variational circuits (QVCs). The model includes a dilated feature extractor that feeds into a parameterized quantum layer for entanglement-preserving transformation. The quantum circuit acts as a regularizer and nonlinear encoder, effectively reducing model complexity and enhancing feature discrimination. The Q-DCN was evaluated on a simulated quantum image dataset and compared against five existing methods: Classical CNN, Dilated CNN, Quantum CNN (QCNN), Variational Quantum Classifier (VQC), and Quantum Kernel Estimator (QKE). Q-DCN achieved superior accuracy (94.3%), reduced inference time by 23%, and utilized 35% fewer parameters. These results indicate that Q-DCN offers a scalable, efficient, and accurate solution for quantum image recognition.
The objective of this research is to develop a Hybrid Quantum-Classical Convolutional Neural Network (QC-CNN) framework that integrates parameterized quantum circuits (PQCs) within classical CNN architectures to enhance image classification performance.The proposed model leverages quantum principles such as superposition and entanglement for high-dimensional feature representation, achieving superior accuracy and reduced computational complexity.Experiments on MNIST and CIFAR-10 datasets demonstrated improved classification accuracy of 98.7% and 82.5%, respectively, surpassing traditional CNNs while reducing training time by 33% and parameters by 45%.Statistical analysis confirmed the significance of these improvements.Visualizations using t-SNE revealed enhanced class separability, and noise perturbation tests validated the model's robustness.The results highlight the hybrid QC-CNN's potential for efficient and scalable quantum-enhanced deep learning applications.Extended evaluations, including quantum-layer-depth analysis, robustness testing, and t-SNE visualization, empirically support the hybrid QC-CNN's effectiveness across varied scenarios.
The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.
Deep learning has achieved significant success in pattern recognition, with convolutional neural networks (CNNs) serving as a foundational architecture for extracting spatial features from images. Quantum computing provides an alternative computational framework, a hybrid quantum-classical convolutional neural networks (QCCNNs) leverage high-dimensional Hilbert spaces and entanglement to surpass classical CNNs in image classification accuracy under comparable architectures. Despite performance improvements, QCCNNs typically use fixed quantum layers without incorporating trainable quantum parameters. This limits their ability to capture non-linear quantum representations and separates the model from the potential advantages of expressive quantum learning. In this work, we present a hybrid quantum-classical-quantum convolutional neural network (QCQ-CNN) that incorporates a quantum convolutional filter, a shallow classical CNN, and a trainable variational quantum classifier. This architecture aims to enhance the expressivity of decision boundaries in image classification tasks by introducing tunable quantum parameters into the end-to-end learning process. Through a series of small-sample experiments on MNIST, F-MNIST, and MRI tumor datasets, QCQ-CNN demonstrates competitive accuracy and convergence behavior compared to classical and hybrid baselines. We further analyze the effect of ansatz depth and find that moderate-depth quantum circuits can improve learning stability without introducing excessive complexity. Additionally, simulations incorporating depolarizing noise and finite sampling shots suggest that QCQ-CNN maintains a certain degree of robustness under realistic quantum noise conditions. While our results are currently limited to simulations with small-scale quantum circuits, the proposed approach offers a potentially promising direction for hybrid quantum learning in near-term applications.
A digital recognition paradigm integrating a hybrid quantum-traditional neural network is developed for numerical recognition, whereby quantum computing and conventional neural networks may collaborate. This model integrates parameterized quantum circuits within a convolutional framework to attain a combination of embedding and direct output. The input from the convolutional fully connected layer functions as the control parameter for the quantum layer and is subjected to a sequence of transformations for feature processing. This structure's potential is evidenced by digit recognition on the MNIST dataset for digital applications. The approach employs transfer learning, integrating convolutional and deep image feature extraction using hybrid networks, thereby mitigating the overfitting problem associated with a singular convolutional network on limited sample datasets. The findings demonstrate the model's efficacy, utility, and superior generalization capability. The recognition rates of the direct output hybrid network and the embedded hybrid network on the MNIST dataset increased by 0.0398 and 0.0211, respectively, in comparison to a convolutional network. Following transfer learning and feature fusion, the recognition rates of the hybrid model on small sample datasets exceed those of a singular network, achieving 83%, so validating the model's learning and generalization proficiency for digital applications.
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).