Expectation-value quantum classifiers form a broad class of supervised quantum machine learning models in which predictions are obtained from observables measured on parameterized quantum states. When expressed in a fixed operator basis, these models are equivalent to linear classifiers in an induced feature space, with weights determined by quantum expectation values. Within this setting, the empirical role of architectural design choices remains insufficiently understood.We study how circuit architecture influences performance in quantum-generated linear classifiers for image classification. Classical images are mapped to Pauli feature representations and weight matrices are generated by variational quantum circuits. A full factorial design evaluates five factors: feature representation, circuit capacity (number of circuits K), depth, ansatz family, and initialisation. Additive and interaction effects are quantified using analysis of variance on MNIST and Fashion-MNIST.Results show that capacity contributes primarily through additive logarithmic scaling, while circuit geometry and initialisation determine interaction structure. Feature representation has limited standalone impact but modulates architectural sensitivity. These findings provide a systematic empirical characterisation of architectural behaviour in quantum-generated linear classifiers.
Expectation-value quantum classifiers form a broad class of supervised quantum machine learning models in which predictions are obtained from observables measured on parameterized quantum states. When expressed in a fixed operator basis, these models are equivalent to linear classifiers in an induced feature space, with weights determined by quantum expectation values. Within this setting, the empirical role of architectural design choices remains insufficiently understood.We study how circuit architecture influences performance in quantum-generated linear classifiers for image classification. Classical images are mapped to Pauli feature representations and weight matrices are generated by variational quantum circuits. A full factorial design evaluates five factors: feature representation, circuit capacity (number of circuits K), depth, ansatz family, and initialisation. Additive and interaction effects are quantified using analysis of variance on MNIST and Fashion-MNIST.Results show that capacity contributes primarily through additive logarithmic scaling, while circuit geometry and initialisation determine interaction structure. Feature representation has limited standalone impact but modulates architectural sensitivity. These findings provide a systematic empirical characterisation of architectural behaviour in quantum-generated linear classifiers.
This research explores quantum machine learning for image classification, comparing classical and quantum models. A classical convolutional neural network (CNN), based on the LeNet architecture, achieved 99.12% accuracy on MNIST, outperforming a quantum CNN, which attained 93.30%. Quantum encoders applied to Fashion-MNIST reached 85.60%, while quantum support vector machine (SVM), implemented for binary classification, obtained 71.34%. The study integrates hybrid quantum-classical models, leveraging quantum circuits for feature extraction. A quantum autoencoder-based classifier was introduced, demonstrating efficient data compression and classification without additional qubits. Feature encoding using RX gates mapped classical data into quantum states, and the impact of parameterized quantum circuit structures on classification accuracy was analyzed. Results indicate that specific ansatz structures yield superior accuracy, highlighting the significance of quantum circuit design. While classical models currently outperform quantum counterparts, quantum approaches reduce trainable parameters and computational complexity. Limitations in current quantum hardware, including noise and scalability, restrict performance. However, advancements in error mitigation, quantum gate efficiency, and scalable quantum architecture could bridge the gap with classical methods. These quantum techniques hold potential in aerospace applications, such as satellite image classification, anomaly detection in remote sensing, and real-time processing of high-dimensional image data. This study underscores the growing role of quantum circuits in machine learning, particularly in feature extraction and classification, suggesting that future quantum hardware could unlock new capabilities in end-to-end learning beyond hybrid approaches.
Image-based quantum machine learning usually follows a hybrid pipeline: a classical encoder compresses an image, and a quantum circuit then acts as a kernel, feature map, trainable classifier, or measurement-based readout. Yet it remains unclear which of these roles contributes useful predictive structure because prior studies often change the input representation, classical baseline, and measurement budget simultaneously. We present a controlled benchmark spanning five roles: quantum-kernel geometry, fixed product and entangled features, trainable data-reuploading representations, shot-aware probability readout, and task-adaptive Pauli measurement. Six quantum-derived methods, six matched classical controls, and two unmatched neural references are evaluated on MNIST, Fashion-MNIST, CIFAR-10, and BreastMNIST using a shared frozen ResNet-18 and train-only PCA interface. We assess exact and finite-shot inference, predictive performance, calibration, selective risk, resource requirements, and statistical reliability. PdrQC-Matched was the strongest quantum-derived method on all four datasets. C-RBF was better on Fashion-MNIST and CIFAR-10 by 2.19 and 3.50 accuracy points, while BreastMNIST showed no detectable difference. Despite lower exact accuracy, PdrQC-Matched achieved significantly lower Brier score and AURC than C-RBF on Fashion-MNIST and CIFAR-10. Finite-shot results showed no automatic benefit from entanglement or shot-aware training. Overall, image-QML conclusions depend on quantum role, measurement budget, classical control, and evaluation metric.
Variational quantum classifiers combine parameterised quantum circuits with classical optimisa-tion to perform supervised classification, but their practical performance depends strongly on circuit architecture, trainability, and hardware-resource requirements. Current noisy intermediate-scalequantum devices further constrain these models through limited usable circuit depth, hardwarenoise, and expensive quantum-circuit evaluations, motivating systematic benchmarking undercontrolled conditions.This thesis investigates how the structure of an interaction-based ansatz influences the behaviourof a hybrid quantum–classical classifier. A ZZ-only IsingZZ ansatz is compared with the proposed Arivoli ansatz, which combines XX-, Y Y -, and ZZ-type interaction channels between neigh-bouring qubits. The primary architecture comparison uses IsingZZ with three repeated nearest-neighbour ladders and Arivoli with one ladder, with nine nominal optimisation parameters in each implementation.Classical data are reduced to four features and encoded on four qubits using arcsin-RY rotations.The resulting quantum states are processed by the parameterised ansatz and measured usingAll-Qubit Multi-Observable Measurement (AMM), producing X-, Y -, and Z-expectation valuesthat are classified by a linear softmax readout. The architectures are evaluated on benchmark classification datasets using predictive performance, optimisation behaviour, expressibility, en-tangling capability, and circuit-resource metrics. Classical baselines and IBM Quantum execution are additionally used to assess the practical relevance and hardware behaviour of the proposedframework.The study does not seek to demonstrate quantum advantage. Instead, it examines the trade-offs between representational capability, optimisation behaviour, classification performance, and hard-ware cost in variational quantum classifier design. The results are used to assess whether richer multi-axis interactions provide practically useful behaviour under near-term quantum-computingconstraints.
Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum circuit architecture, a choice that remains largely manual. Most existing approaches rely on hand-designed or fixed circuit ansätze, requiring circuit structure, gate composition, and qubit connectivity to be specified in advance with no guarantee that they suit the task. This limitation is especially acute in image classification, where quantum circuits must transform features extracted by classical networks while remaining compact enough for practical training, requirements that generic, task-agnostic ansätze are unlikely to satisfy simultaneously. We extend EXAQC, an evolutionary framework for automated quantum circuit discovery, to image classification. EXAQC evolves PQCs as intermediate processing modules while retaining classical feature-extraction and prediction layers. On MNIST, Fashion-MNIST, and CIFAR-10, EXAQC achieves 98.42%, 90.62%, and 85.47% accuracy, respectively, while using comparable gate counts to other quantum architecture-search methods. Against classical networks, evolved hybrid models maintain comparable accuracy with substantially fewer trainable parameters, reaching 85.68% on CIFAR-10 with over 25× fewer parameters than a 10-layer CNN. Encoding choice also matters: rotation-based encodings (RX, RY, U3) outperform amplitude encoding by 22-25 points on CIFAR-10. These results demonstrate that automated circuit discovery yields compact quantum modules that can replace larger classical components in vision architectures while retaining competitive accuracy.
The expressivity and scalability of fixed feature embeddings and shallow quantum circuits for Quantum Support Vector Machines (QSVMs) are restricted due to the limitations of near-term hardware. In this work, we propose a novel QSVM framework consisting of Low-Rank Adaptation (LoRA)-modified VisionTransformer embeddings as well as trainable variational quantum circuits. The architecture enhances the representational power by the joint optimization of embedding and circuit parameters. Empirical evaluation on distilled benchmark datasets shows significant performance gains, with up to 38.7% absolute accuracy improvement on MNIST (61.3% to 100.0%). The model also achieves 91% to 100% test accuracies on Fashion-MNIST, KMNIST and CIFAR-10 datasets with only 200 training samples for each dataset. The results show that the performance improvements are due to the joint design between the feature embeddings and the quantum circuits, rather than just the quantum kernels. Cross-dataset evaluations and circuit-depth analyses provide experimental evidence that the approach is suitable for scalable quantum machine learning in image classification tasks.
Variational quantum algorithms have gained attention as early applications of quantum computers for learning tasks. In the context of supervised learning, most of the works that tackle classification problems with parameterized quantum circuits constrain their scope to the setting of binary classification or perform multiclass classification via ensembles of binary classifiers (strategies such as one versus rest). Those few works that propose native multiclass models, however, do not justify the choice of observables that perform the classification. This work studies two main classification criteria in multiclass quantum machine learning: maximizing the expected value of an observable representing a class or maximizing the fidelity of the encoded quantum state with a reference state representing a class. To compare both approaches, sets of Pauli strings and sets of projectors into the computational basis are chosen as observables in the quantum machine learning models. Observing the empirical behavior of each model type, the effect of different observable set choices on the performance of quantum machine learning models is analyzed in the context of Barren Plateaus and Neural Collapse. The results provide insights that may guide the design of future multiclass quantum machine learning models.