Abstract In this study, we investigate a simple quantum pre-processing filter kernel designed with only two CNOT gates for image feature extraction. We examine the impact of these filters when combined with a classical neural network for image classification tasks.Our main hypothesis is that this circuit can extract pixel correlation information that classical filters cannot. This approach is akin to a convolutional neural network, but with quantum layers replacing convolutional layers to extract spatial pixel entanglement. We found that a small circuit with just two CNOT gates can be engineered in three different spatial symmetries, each affecting classification differently. While the filter improves classification when combined with a simple, narrow network, it does not surpass complex classical methods. However, the filter demonstrates potential to enhance classification performance in more sophisticated architectures. Despite this, our empirical results show no clear correlation between the observed improvements and the level of entanglement in the quantum circuit, as measured by Von Neumann Entropy. The underlying cause of this improvement remains unclear and warrants further investigation.
Abstract In this study, we investigate a simple quantum pre-processing filter kernel designed with only two CNOT gates for image feature extraction. We examine the impact of these filters when combined with a classical neural network for image classification tasks.Our main hypothesis is that this circuit can extract pixel correlation information that classical filters cannot. This approach is akin to a convolutional neural network, but with quantum layers replacing convolutional layers to extract spatial pixel entanglement. We found that a small circuit with just two CNOT gates can be engineered in three different spatial symmetries, each affecting classification differently. While the filter improves classification when combined with a simple, narrow network, it does not surpass complex classical methods. However, the filter demonstrates potential to enhance classification performance in more sophisticated architectures. Despite this, our empirical results show no clear correlation between the observed improvements and the level of entanglement in the quantum circuit, as measured by Von Neumann Entropy. The underlying cause of this improvement remains unclear and warrants further investigation.
This study explores Quantum Convolutional Neural Network (QCNN) starting from foundational quantum operations, such as the Rx gate for encoding MNIST image data into quantum states. We implemented quantum convolutional and pooling layers using one_unitary and two_unitary circuits, enabling effective feature extraction and dimensionality reduction while preserving critical information. Expressibility analysis revealed varying capabilities across different one_unitary circuits, with Rx, Ry, and Rz combinations demonstrating promising results akin to Haar random states. The proposed QCNN model exhibited robust performance metrics (accuracy: 95.98%, precision: 94.44%, recall: 96.59%, F1-score: 0.9551, AUC: 0.9604) in classification tasks, supported by efficient convergence during optimization. Future directions include expanding QCNN applications to handle more complex datasets and optimizing architectures to enhance quantum machine learning capabilities, particularly in image processing. This study underscores the potential of QCNNs in advancing quantum computing applications in neural network architectures. Keywords: MNIST, classification, CNN, expressibility
Convolutional neural networks (CNNs) are extensively employed for tasks such as image processing, employing a hierarchical feature extraction approach facilitated by convolutional layers. A recent trend explores quantum counterparts called Quanvolutional layers, utilizing random quantum circuits akin to convolutional filter layers. Our work advances this by introducing structured entanglement in quanvolutional layers using Basic and Strongly Entangled Layers. Unlike random circuit approaches, these layers have defined structures and high entanglement, requiring minimal error correction. We evaluated their performance on MNIST dataset, comparing various techniques like traditional CNNs, Quanvolutional Neural Networks (QNNs) with Random quantum circuits, basic entangled layers, strongly entangled layers. Structured entanglement shows promise in improving feature extraction for QNNs, providing insights into their understanding. Our work explores the use of structures quantum layers in constructing quantum-classical hybrid architectures and evaluates their performance. Future research may explore scalability and applicability in complex datasets and integration with other quantum computing techniques for enhanced performance and versatility.
In recent years, there has been a growing interest in leveraging the unique properties of quantum computing to develop novel machine learning algorithms and architectures. This research paper presents an investigation of quantum convolutional neural networks (QCNNs), which leverage the unique properties of quantum computing to potentially improve the accuracy and efficiency of image classification tasks. Specifically, the paper explores three different QCNN architectures, including a pure quantum-based QCNN, a hybrid QCNN with a single quantum convolution layer, and a hybrid convolutional architecture with multiple quantum filters. We tested the models on MNIST dataset and the results of the study demonstrate that hybrid architectures that combine quantum and classical processing are more effective than pure quantum-based architectures in image classification tasks. In particular, the third model, the Hybrid Convolution with Multiple Quantum Filters, achieved the highest test set accuracy of 92.7%. The use of multiple quantum filters in conjunction with a classical neural network resulted in enhanced accuracy and efficiency in image classification tasks, highlighting the potential of hybrid architectures for future applications in machine learning tasks.
This paper explores the performance of quantum-classical hybrid networks in image classification tasks, focusing on the integration of quantum circuits as alternative feature extractors to traditional convolutional layers. Specifically, it investigates the use of quanvolutional layers, variational quantum circuits that leverage quantum entanglement and quantum gates, in comparison to classical layers. The study examines various quantum pooling techniques, including conditional entanglement gates, and their impact on classification accuracy across datasets with varying complexity. By experimenting with different pooling strategies, both parametrized and non-parametrized, this work assesses their influence on network performance and feature representation. Results indicate that quanvolutional layers in a hybrid network consistently outperform classical convolutional layers in terms of classification accuracy, particularly when applied to datasets with prominent features. Additionally, the findings suggest that quantum entanglement techniques, rather than rotation parameters, play a more significant role in enhancing performance. This paper concludes that quantum-classical hybrid networks offer a promising approach for feature extraction, although the optimal configuration of pooling methods depends on the characteristics of the data. Future research could further explore the interplay between quantum circuits and different pooling strategies for more effective feature representation.
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.
Recent advancements in quantum machine learning have spurred the development of hybrid quantum-classical convolutional neural networks (HQCCNNs), which have demonstrated promising potential for image classification tasks. Building on the operational principles of classical transposed convolutional neural networks (CNNs), we introduce a novel quantum variant: the Quantum Pseudo-Transposed Convolutional Neural Network (QPTCNN). The QPTCNN adapts the concept of classical transposed CNNs to the quantum domain, leveraging a hybrid quantum-classical framework that combines a quantum convolutional layer with a classical fully connected layer. In the QPTCNN, the quantum convolutional layer emulates a transposed convolution operation, ensuring that the output feature map retains the same dimensions as the input image. This is accomplished using rotational angle encoding and a ring-structured quantum circuit, interconnected by two-qubit control gates such as CNOT and CRY gates, facilitating efficient quantum convolution. We evaluated the performance of the QPTCNN on the MNIST and Fashion-MNIST datasets, with two distinct versions of the model: Model A, which utilizes a CNOT-gate entanglement circuit, and Model B, which employs a CRY-gate entanglement circuit. The results demonstrate that both Model A and Model B achieve strong performance across the datasets. However, Model A outperforms Model B, achieving higher classification accuracy and lower loss compared to earlier models. These findings suggest that the QPTCNN is highly capable of learning and extracting relevant feature information from input images, making it well-suited for high-performance image classification tasks. This work represents a significant advancement in quantum-enhanced image classification.