This work investigates whether classical machine learning can detect statistical signatures associated with entanglement graph structure from partial quantum measurements. Experiments were performed on real IBM Quantum hardware using circuits with controlled entanglement patterns. Only a subset of qubits was observed, while the state of one qubit was hidden. A classical Random Forest classifier was trained to predict the hidden qubit’s measurement outcome based solely on the observed subset. To distinguish structural effects from spatial or hardware-related confounders, a geometry decoupling protocol was introduced. This involved comparing entangled circuits with control circuits of identical spatial layout but without entangling gates. Results show that classification accuracy exceeds chance in entangled configurations and correlates negatively with graph distance, suggesting that classical models can capture statistical signatures consistent with entanglement connectivity. The introduced delta metric partially controls for hardware bias by comparing entangled and non-entangled baselines. The observed signal reflects classical correlations in measurement outcomes generated by entangled states and does not constitute quantum communication or violation of no-signalling principles. This dataset and code provide a reproducible experimental framework for studying the relationship between quantum circuit structure and classical detectability using machine learning.
This work investigates whether classical machine learning can detect statistical signatures associated with entanglement graph structure from partial quantum measurements. Experiments were performed on real IBM Quantum hardware using circuits with controlled entanglement patterns. Only a subset of qubits was observed, while the state of one qubit was hidden. A classical Random Forest classifier was trained to predict the hidden qubit’s measurement outcome based solely on the observed subset. To distinguish structural effects from spatial or hardware-related confounders, a geometry decoupling protocol was introduced. This involved comparing entangled circuits with control circuits of identical spatial layout but without entangling gates. Results show that classification accuracy exceeds chance in entangled configurations and correlates negatively with graph distance, suggesting that classical models can capture statistical signatures consistent with entanglement connectivity. The introduced delta metric partially controls for hardware bias by comparing entangled and non-entangled baselines. The observed signal reflects classical correlations in measurement outcomes generated by entangled states and does not constitute quantum communication or violation of no-signalling principles. This dataset and code provide a reproducible experimental framework for studying the relationship between quantum circuit structure and classical detectability using machine learning.
This paper explores the use of machine learning techniques for detecting quantum entanglement in two-qubit systems. A dataset of randomly generated quantum states was constructed and labeled using the Positive Partial Transpose (PPT) criterion. Several supervised learning models, including Random Forest and Multi-Layer Perceptron neural networks, were trained to classify quantum states as entangled or separable. The results show that machine learning models can effectively learn patterns from quantum state data, while also highlighting the impact of dataset imbalance on classification performance. This study demonstrates the potential of machine learning as a complementary tool for quantum entanglement detection and provides insights into the challenges and opportunities of integrating artificial intelligence with quantum physics.
Quantum machine learning (QML) investigates whether quantum-mechanical representations and computations can improve machine-learning tasks. However, it is often unclear which observed performance differences are genuinely attributable to specifically quantum features rather than to architectural differences that can be implemented classically or benchmarking effects. This thesis studies the role of entanglement in variational QML models through a controlled ablation or removal framework. The work introduces partially and fully separable variants of the Circuit-centric Classifier (CCC) and IQP-Kernel Classifier, constructed by systematically reducing entangling interactions while keeping the remaining training and evaluation pipeline fixed. The models are evaluated on multiple synthetic and structured benchmark families, including but not limited to linearly separable, hidden-manifold, and hyperplane-based datasets. The results show that partially entangling variants often remain competitive with the original models, whereas fully separable variants typically exhibit larger performance degradation. The experiments are consistent with entanglement contributing meaningfully to performance in the studied models, while also suggesting that sparse entangling connectivity may already retain much of the observed benefit of the original architectures in this benchmark setting. The IQP-kernel experiments scaled prohibitively in higher-dimensional settings, exceeding the available computational budget.
Detecting and quantifying quantum entanglement remain significant challenges in the noisy intermediate-scale quantum (NISQ) era. This study presents the implementation of quantum support vector machines (QSVMs) on IBM quantum devices to identify and classify entangled states. By employing quantum variational circuits, the proposed framework achieves a runtime complexity of [Formula: see text], where N is the number of qubits, t is the number of iterations, and ε is the acceptable error margin. We investigate various quantum circuits with multiple blocks and obtain the accuracy of QSVM as measures of expressibility and entangling capability. Our results demonstrate that the QSVM framework achieves over 90% accuracy in distinguishing entangled states, despite hardware noise such as decoherence and gate errors. Benchmarks across superconducting qubit platforms (e.g., IBM Perth, Lagos, and Nairobi) highlight the robustness of the model. Furthermore, the QSVM framework effectively classifies two-qubit states and extends its predictive capabilities to three-qubit entangled states. This work marks a significant advancement in quantum machine learning for entanglement detection.
This thesis presents a comparative study of quantum machine learning and classical machine learning developed from first principles. It begins by establishing the foundations of the quantum circuit model, observables, and projective measurement, and then revisits the classical learning framework with an emphasis on risk minimisation, task-aligned metrics, and rigorous evaluation protocols. Building on this shared perspective, the thesis examines two central paradigms in quantum machine learning: quantum kernels and variational quantum circuits. A unifying theme is that quantum models must be assessed fairly against strong classical baselines and under realistic hardware constraints. The work therefore explicitly accounts for the limitations of noisy intermediate-scale quantum (NISQ) devices, including noise, restricted connectivity, compilation overhead, and finite-shot estimation. The empirical study instantiates both quantum pipelines on a controlled supervised benchmark adapted from IBM Quantum: classifying small synthetic images containing either a vertical or a horizontal line under bounded noise. Using the same dataset, identical splitting strategies, and matched budgets for shots and optimisation, the thesis compares quantum and classical models under a consistent evaluation protocol. The results show that both quantum kernel and variational approaches achieve meaningful accuracy in this regime, but do not demonstrate a decisive quantum advantage on the selected task. The thesis concludes by outlining limitations and directions for future work, including scaling to richer benchmarks, incorporating error mitigation, and strengthening assumption-explicit methodology for credible claims of quantum-enhanced learning.
Quantum kernel methods encode classical data into quantum states using specially designed feature-map circuits and then train a classical SVM on the resulting kernel matrix. Prior studies of entanglement structure typically compare only a few basic topologies, such as linear, circular, and full entanglement, leaving the broader space of entanglement graphs largely unexplored. This study exhaustively evaluates all possible entanglement topologies of a TwoLocal feature map and benchmarks them against classical methods and standard quantum feature maps on two synthetic datasets (Adhoc3_150 and Adhoc4_150) and two real-world datasets (Blood and Banknote). On Adhoc4_150, the best TwoLocal topology achieves an accuracy of 0.7556, matching Pauli Z; on Blood, it reaches 0.6889, exceeding RBF SVM and Pauli Z at 0.6667; and on Banknote, it achieves 1.0000, compared with 0.9778 for RBF SVM. In contrast, Random Forest achieves the highest accuracy on Adhoc3_150 at 0.8222, exceeding all evaluated quantum configurations. Across all four datasets, increasing the number of entangling pairs does not consistently improve accuracy, while the standard linear, circular, and full Pauli ZZ topologies never outperform Pauli Z. To further characterize this behavior, we propose a factorial linear modeling approach that quantifies the contribution of individual entanglement edges and qubit connectivity to classification accuracy. On Adhoc4_150, two edges exhibit significant negative effects, whereas Blood and Banknote show both significant positive and negative edge effects. The q0q1 edge is significant across all three four-feature datasets but reverses direction across datasets. These results indicate that the effect of entanglement depends jointly on the feature-map architecture, dataset, and specific qubit connections rather than on entanglement density alone. The proposed framework can also be applied to sampled topology sets, providing a basis for targeted entanglement analysis beyond exhaustively enumerable low-qubit systems.
The thesis explores the development of the Quantum Pattern Extraction and Classification (QPEC) algorithm, a hybrid quantum-classical method designed to classify devices based on their PWM signals. In cybersecurity, the QPEC algorithm can identify PWM signal distortion for device authentication and in fault detection by recognizing subtle signal anomalies that indicate hardware degradation. The research addresses the challenge of accurately identifying subtle differences in PWM signals, which classical methods struggle to handle effectively. The Primary research question investigates whether quantum computing can enhance feature extraction and improve classification accuracy compared to traditional approaches. To achieve this, the QPEC algorithm utilizes a parameterized quantum circuit (PQC) with entanglement layers to map PWM signal features into a high-dimensional quantum space, capturing complex correlations. Classical optimization techniques, including stochastic gradient descent, are applied to refine the quantum circuit parameters, and machine learning models are integrated for classification. The methodology combines quantum simulations, training, and testing on real-world PWM datasets, with performance evaluated using metrics such as accuracy, precision, recall and F1-score. This hybrid quantum-classical approach has a 88.7% accuracy compared to classic state vector machines of 85.3% and random forest classifier of 86.1%.