Recent advances in machine learning have significantly facilitated the study of quantum phases and quantum phase transitions in equilibrium. When applied to dynamical phenomena, both classical and quantum networks demand an extensive cost of resources owing to the inclusion of the temporal dimension. Here, we propose a hybrid quantum‐classical architecture combining a quantum convolutional neural network (QCNN) with a classical neural network (CNN) to study nonequilibrium dynamics, and demonstrate an application of classifying dynamical quantum phase transitions (DQPTs). The QCNN layer of the hybrid network is responsible for extracting spatial features from quantum states at each time step, and the CNN layer processes the temporal sequence of QCNN outputs for classification. For a nearest‐neighbor transverse‐field Ising model, numerical simulations show test accuracy exceeding 95% when identifying DQPTs in quench dynamics, with robustness under single‐ and two‐qubit depolarizing noise. Remarkably, the trained network can be applied without modification to a different Ising model with long–range interaction, showing the potential as a migratable classifier. This hybrid framework circumvents the exponential cost of classical methods and the noise susceptibility of deep quantum circuits, offering a scalable and hardware‐efficient approach for characterizing nonequilibrium dynamics.
Recent advances in machine learning have significantly facilitated the study of quantum phases and quantum phase transitions in equilibrium. When applied to dynamical phenomena, both classical and quantum networks demand an extensive cost of resources owing to the inclusion of the temporal dimension. Here, we propose a hybrid quantum‐classical architecture combining a quantum convolutional neural network (QCNN) with a classical neural network (CNN) to study nonequilibrium dynamics, and demonstrate an application of classifying dynamical quantum phase transitions (DQPTs). The QCNN layer of the hybrid network is responsible for extracting spatial features from quantum states at each time step, and the CNN layer processes the temporal sequence of QCNN outputs for classification. For a nearest‐neighbor transverse‐field Ising model, numerical simulations show test accuracy exceeding 95% when identifying DQPTs in quench dynamics, with robustness under single‐ and two‐qubit depolarizing noise. Remarkably, the trained network can be applied without modification to a different Ising model with long–range interaction, showing the potential as a migratable classifier. This hybrid framework circumvents the exponential cost of classical methods and the noise susceptibility of deep quantum circuits, offering a scalable and hardware‐efficient approach for characterizing nonequilibrium dynamics.
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.
Machine learning has been applied to a wide variety of models, from classical statistical mechanics to quantum strongly correlated systems, for classifying phase transitions. The recently proposed quantum convolutional neural network (QCNN) provides a new framework for using quantum circuits instead of classical neural networks as the backbone of classification methods. We present the results from training the QCNN by the wavefunctions of the variational quantum eigensolver for the one-dimensional transverse field Ising model (TFIM). We demonstrate that the QCNN identifies wavefunctions corresponding to the paramagnetic and ferromagnetic phases of the TFIM with reasonable accuracy. The QCNN can be trained to predict the corresponding ‘phase’ of wavefunctions around the putative quantum critical point even though it is trained by wavefunctions far away. The paper provides a basis for exploiting the QCNN to identify the quantum critical point.
Machine learning has been applied on a wide variety of models, from classical statistical mechanics to quantum strongly correlated systems for the identification of phase transitions. The recently proposed quantum convolutional neural network (QCNN) provides a new framework for using quantum circuits instead of classical neural networks as the backbone of classification methods. We present here the results from training the QCNN by the wavefunctions of the variational quantum eigensolver for the one-dimensional transverse field Ising model (TFIM). We demonstrate that the QCNN identifies wavefunctions which correspond to the paramagnetic phase and the ferromagnetic phase of the TFIM with good accuracy. The QCNN can be trained to predict the corresponding phase of wavefunctions around the putative quantum critical point, even though it is trained by wavefunctions far away from it. This provides a basis for exploiting the QCNN to identify the quantum critical point.
Quantum computing, based on fundamental quantum-mechanical principles and phenomena such as superposition, entanglement, and interference, offers access to high-dimensional quantum feature spaces and complex correlations that may be difficult to efficiently represent using classical computing, along with potential computational advantages through quantum hardware. Therefore, quantum computing has emerged as a promising paradigm for addressing limitations of classical deep learning (DL) through fundamentally different computational mechanisms. Quantum computing-based DL approaches have been applied to image classification; however, most rely on existing quantum computing libraries that impose substantial computational costs, limiting their broader applicability. In this study, hybrid quantum convolutional neural networks (HQCNNs) are proposed for structural damage classification without relying on existing quantum computing libraries. The proposed architectures integrate quanvolutional layers, composed of encoding, variational quantum circuits, and measurement, with conventional convolutional layers in a CNN architecture, enabling quantum-enhanced feature extraction while maintaining compatibility with classical computing systems. The scratch-implemented HQCNN (HQCNN(S)), its library-based counterpart (HQCNN(P)), and the classical CNN are compared in terms of test accuracy, computational cost, and training efficiency. Experimental results demonstrate that HQCNN(S) ( at ) achieves up to 176.57 faster computation than HQCNN(P) and 3.1% higher test accuracy than the classical CNN, while reducing the number of trainable parameters by 60.2%. Moreover, HQCNN(S) achieves comparable performance to the best-performing classical CNN using 75% less training data.
Quantum machine learning is emerging as a promising frontier at the intersection of quantum computing and Artificial Intelligence, offering potential gains in speed, efficiency, and robustness. In this paper, a hybrid Quantum Convolutional Neural Network (QCNN) architecture is presented for visual pattern recognition tasks, leveraging quantum superposition and entanglement for enhanced feature extraction. Unlike previous studies that focus on small-scale or simplified datasets, this study systematically evaluates QCNNs across multiple benchmark datasets and provides a direct comparison with classical CNNs, highlighting practical quantum advantages such as parameter efficiency and noise-resilience. The proposed approach encodes classical image data from benchmark datasets, including70K28×28grayscale images from MNIST and FashionMNIST, and60Kdownsampled grayscale CIFAR-10 images, into quantum states using amplitude encoding, followed by hierarchical quantum convolution and pooling layers implemented via parametrised quantum circuits (PQCs). The model culminates in a classical dense layer for final classification. Experimental results demonstrate that the QCNN achieves competitive performance on low-dimensional grayscale datasets with 93.2 % accuracy on MNIST and 88.5% on Fashion MNIST, though it underperforms on more complex datasets like CIFAR-10 with 67.8 % accuracy due to current quantum hardware limitations. While not yet surpassing classical CNNs in raw accuracy, the proposed QCNN exhibits notable parameter efficiency, noise resilience, and theoretical potential for energy-efficient computation, highlighting its promise for future applications as quantum technologies mature.
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.