Benchmarking MedMNIST dataset on real quantum hardware

This rapid growth in data and the increased complexity of machine learning models have made it almost impossible to continue pushing forward with classical computing, thereby creating a pressing need for new computational paradigms. The following paper will examine how quantum machine learning answers the above questions by applying the principles of quantum mechanics to the art of artificial intelligence (AI) and big data analytics. We examine some of the current Quantum Machine Learning (QML) algorithms and their applications based on a framework that employs quantum-enhanced feature spaces, variational quantum circuits, and quantum-inspired classical algorithms. Our methodology combines theoretical analysis with empirical evaluation of these methods over standard benchmark datasets, using both quantum simulators and real quantum hardware. Key findings include a set of advantages carried by QML in specific fields, such as dimensionality reduction, optimization problems, and some clustering tasks. These are the quadratic speedup for support vector machines and the exponential advantage for principal component analysis. Our results also show that quantum error correction isn’t perfect and that loading classical data into a quantum system can be hard. We conclude that, while QML holds much promise, it is, by all means, clearly still a way off from being considered a panacea. It is awaiting further breakthroughs in quantum hardware, error mitigation techniques, and algorithm design in order to fully realize its potential. This work thus presents a roadmap for future research and highlights where QML is best placed to make major impactful differences in artificial intelligence and big data analytics.

Quantum machine learning (QML) has emerged as a promising field, combining the power of quantum computing with classical machine learning techniques to solve complex computational tasks. As the demand for efficient quantum simulations grows, multiple QML frameworks, including PennyLane, Qiskit, and TensorFlow Quantum (TFQ), have been developed to facilitate hybrid quantum-classical computations. This study aims to evaluate and compare the performance of three leading QML frameworks PennyLane, Qiskit, and TensorFlow Quantum in simulating quantum machine learning models, focusing on accuracy, execution time, and noise tolerance. The study examined three leading quantum machine learning (QML) frameworks PennyLane (v0.24), Qiskit (v0.43.2), and TensorFlow Quantum (TFQ, v0.7) each tested on a 64-bit Ubuntu Linux system with an Intel Core i7 processor, 32 GB RAM, and NVIDIA GeForce RTX 3080 GPU. Quantum algorithms like variational quantum circuits (VQCs) and quantum support vector machines (QSVMs) were simulated using these frameworks. Various quantum gates, including Pauli-X, Y, Z, Hadamard, CNOT, and Rotation gates (Rx, Ry, Rz), were used for parameter optimization and quantum superposition. The Iris and MNIST datasets were adapted for quantum encoding using Amplitude and Angle Encoding for binary classification tasks. Simulations were run on classical computers, while select circuits were executed on IBM Quantum’s Falcon r5.11 processor to compare hardware performance. PennyLane achieved the highest accuracy (92%) in quantum simulations, excelling in hybrid quantum-classical model integration. TensorFlow Quantum provided the fastest execution time, especially in classical simulations, making it suitable for rapid prototyping. Qiskit produced deeper quantum circuits but had higher error rates (6%) on real quantum hardware, highlighting noise and decoherence effects. The VQC models optimized by stochastic gradient descent (SGD) showed significant improvements in model performance, and QSVMs effectively classified both linearly separable and non-separable datasets, demonstrating the potential of quantum algorithms over classical approaches. Statistical analysis confirmed the significance of the results (p < 0.05). PennyLane is the most robust framework for hybrid quantum-classical models, while TensorFlow Quantum is suited for rapid prototyping. Qiskit, despite longer execution times, excels in hardware implementation. The choice of framework should align with the specific needs of quantum machine learning tasks.

This study evaluates gate-based quantum machine learning (QML) models, including the Variational Quantum Classifier (VQC) and Quantum k-Nearest Neighbors (QkNN), on the QM9 quantum chemistry dataset for binary classification of molecular electronic properties. Using IBM Qiskit, both models were tested on simulators and real quantum hardware. Classical models (LightGBM, SVM, MLP) served as benchmarks. Results show classical models outperform quantum ones, with LightGBM achieving the highest AUC-ROC (0.901). However, VQC on simulators achieved a competitive AUC of 0.781, and real hardware still yielded performance above that of chance. Despite hardware constraints, quantum models demonstrated learning capability. The findings support hybrid quantum-classical systems as a promising near-term approach while quantum hardware continues to evolve

The real-time simulation of large many-body quantum systems is a formidable task, that may only be achievable with a genuine quantum computational platform. Currently, quantum hardware with a number of qubits sufficient to make classical emulation challenging is available. This condition is necessary for the pursuit of a so-called quantum advantage, but it also makes verifying the results very difficult. In this paper, we flip the perspective and utilize known theoretical results about many-body quantum critical dynamics to qualitatively benchmark digital quantum hardware and various error mitigation techniques. In particular, we benchmark against known universal scaling laws in the Hamiltonian simulation of a time-dependent transverse-field Ising Hamiltonian of up to 133 qubits. Incorporating only basic error mitigation and suppression methods, our study shows reliable control up to a two-qubit gate depth of 28, featuring a maximum of 1396 two-qubit gates, before noise becomes prevalent. These results are transferable to applications such as Hamiltonian simulation, variational algorithms, optimization, or quantum machine learning. We demonstrate this on the example of digitized quantum annealing for optimization and identify an optimal working point in terms of both circuit depth and time step on a 133-site optimization problem. Published by the American Physical Society 2024

Quantum Machine Learning was born during the past decade as the intersection of Quantum Computing and Machine Learning. Today, advances in quantum computer hardware and the design of simulation frameworks able to run quantum algorithms in classic computers make it possible to extend classic artificial intelligence models to a quantum environment. Despite these achievements, several questions regarding the whole quantum machine learning pipeline remain unanswered, for instance the problem of classical data representation on quantum hardware, or the methodologies for designing and evaluating quantum models for common learning tasks such as classification, function approximation, clustering, etc. These problems become even more difficult to solve in the case of Time Series processing, where the context of past historical data may influence the behavior of the decision-making model. In this piece of research, we address the problem of Time Series classification using quantum models, and propose an efficient and compact representation of time series in quantum data using amplitude embedding. The proposal is capable of representing a time series of length n in log2(n)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$log_2(n)$$\\end{document} computational units, and experiments conducted on benchmark time series classification problems show that quantum models designed for classification can also outperform the accuracy of classic methods.

Zero-day attacks pose a persistent threat to computing infrastructure by exploiting previously unknown software vulnerabilities that evade traditional signature-based network intrusion detection systems (NIDSs). To address this limitation, machine learning (ML) techniques offer a promising approach for enhancing anomaly detection in network traffic. This study evaluates several ML models on a labeled network traffic dataset, with a focus on zero-day attack detection. Ensemble learning methods, particularly eXtreme gradient boosting (XGBoost), achieved perfect classification, identifying all 6231 zero-day instances without false positives and maintaining efficient training and prediction times. While classical support vector machines (SVMs) performed modestly at 64% accuracy, their performance improved to 98% with the use of the borderline synthetic minority oversampling technique (SMOTE) and SMOTE + edited nearest neighbours (SMOTEENN). To explore quantum-enhanced alternatives, a quantum SVM (QSVM) is implemented using three-qubit and four-qubit quantum circuits simulated on the aer_simulator_statevector. The QSVM achieved high accuracy (99.89%) and strong F1-scores (98.95%), indicating that nonlinear quantum feature maps (QFMs) can increase sensitivity to zero-day exploit patterns. Unlike prior work that applies standard quantum kernels, this study introduces a parameterised quantum feature encoding scheme, where each classical feature is mapped using a nonlinear function tuned by a set of learnable parameters. Additionally, a sparse entanglement topology is derived from mutual information between features, ensuring a compact and data-adaptive quantum circuit that aligns with the resource constraints of noisy intermediate-scale quantum (NISQ) devices. Our contribution lies in formalising a quantum circuit design that enables scalable, expressive, and generalisable quantum architectures tailored for zero-day attack detection. This extends beyond conventional usage of QSVMs by offering a principled approach to quantum circuit construction for cybersecurity. While these findings are obtained via noiseless simulation, they provide a theoretical proof of concept for the viability of quantum ML (QML) in network security. Future work should target real quantum hardware execution and adaptive sampling techniques to assess robustness under decoherence, gate errors, and dynamic threat environments.

Quantum machine learning (QML) is an emerging field that promises advantages such as faster training, improved reliability and superior feature extraction over classical counterparts. However, its implementation on quantum hardware is challenging due to the noise inherent in these systems, necessitating the use of quantum error correction (QEC) codes. Current QML research remains primarily theoretical, often assuming noise-free environments and offering little insight into the integration of QEC with QML implementations. To address this, we investigate the performance of a simple, parity-classifying Variational Quantum Classifier (VQC) implemented with the [[4,2,2]] error-detecting stabiliser code in a simulated noisy environment. To our knowledge, this is the first implementation of a stabiliser-based error detection code to a QML algorithm. We invoke ancilla qubits to logically encode rotation gates, and classically simulate the logically-encoded VQC under two simple noise models representing gate noise and environmental noise. We demonstrate that the stabiliser code improves the training accuracy at convergence compared to noisy implementations without error detection. However, we find that the effectiveness and reliability of error detection is contingent upon keeping the ancilla qubit error rates below a specific threshold, due to the propagation of ancilla errors to the physical qubits. Our results provide an important insight that extends to QML implemented with full error-correction: when the QEC code requires ancilla qubits for logical rotations but cannot fully correct errors propagated between ancilla and physical qubits, the maximum achievable accuracy of the QML model is constrained. This highlights the need for additional error correction or mitigation strategies to support the practical implementation of QML algorithms with QEC on quantum devices.

Quantum machine learning (QML) is an emerging field combining quantum computing and artificial intelligence, with promising applications in medicine and healthcare. This survey reviews more than 60 studies published between 2018 and 2025, highlighting a sharp increase in research activity, especially in the last three years. We address seven core research questions related to publication trends, the use of real quantum hardware versus simulators, quantum architectures overview, dataset types, medical domains, algorithmic frameworks, and reported results. Our analysis shows that most QML research in healthcare is conducted on simulators due to limited hardware access, and it relies on small datasets. Quantum convolutional neural network (QCNN) architectures dominate image-based medical tasks such as tumor detection, pneumonia diagnosis, and ECG interpretation, while feature-based datasets are mainly analyzed with variational quantum classifiers and quantum support vector machines. Despite hardware constraints, QML models often match or surpass classical machine learning approaches in accuracy, frequently reaching 95–99%. However, these performance statements should be qualified to recognize experimental limitations and avoid excessive optimism and should not be interpreted as definitive proof of quantum superiority at this stage. Additionally, issues with reproducibility and reporting of hardware details persist, which is a significant research gap. This review emphasizes the need for standardized benchmarks, more real hardware testing, and architecture-aware algorithm design. With the potential for accelerated diagnostics and personalized healthcare, QML represents a strategic direction for future medical research.

Quantum machine learning (QML) has emerged as a promising approach for enhancing image classification by exploiting quantum computational principles such as superposition and entanglement. However, practical applications on complex datasets like CIFAR-100 remain limited due to the low expressivity of shallow circuits and challenges in circuit optimization. In this study, we propose HQCNN–REGA—a novel hybrid quantum–classical convolutional neural network architecture that integrates data re-uploading and genetic algorithm optimization for improved performance. The data re-uploading mechanism allows classical inputs to be encoded multiple times into quantum states, enhancing the model’s capacity to learn complex visual features. In parallel, a genetic algorithm is employed to evolve the quantum circuit architecture by optimizing gate sequences, entanglement patterns, and layer configurations. This combination enables automatic discovery of efficient parameterized quantum circuits without manual tuning. Experiments on the MNIST and CIFAR-100 datasets demonstrate state-of-the-art performance for quantum models, with HQCNN–REGA outperforming existing quantum neural networks and approaching the accuracy of advanced classical architectures. In particular, we compare our model with classical convolutional baselines such as ResNet-18 to validate its effectiveness in real-world image classification tasks. Our results demonstrate the feasibility of scalable, high-performing quantum–classical systems and offer a viable path toward practical deployment of QML in computer vision applications, especially on noisy intermediate-scale quantum (NISQ) hardware.

Medical decision-making is increasingly integrating quantum computing (QC) and machine learning (ML) to analyze complex datasets, improve diagnostics, and enable personalized treatments. While QC holds the potential to accelerate optimization, drug discovery, and genomic analysis as hardware capabilities advance, current implementations remain limited compared to classical computing in many practical applications. Meanwhile, ML has already demonstrated significant success in medical imaging, predictive modeling, and decision support. Their convergence, particularly through quantum machine learning (QML), presents opportunities for future advancements in processing high-dimensional healthcare data and improving clinical outcomes. This review examines the foundational concepts, key applications, and challenges of these technologies in healthcare, explores their potential synergy in solving clinical problems, and outlines future directions for quantum-enhanced ML in medical decision-making.

Over the past few years, several quantum software stacks (QSS) have been developed in response to rapid hardware advances in quantum computing. A QSS includes a quantum programming language, an optimizing compiler that translates a quantum algorithm written in a high-level language into quantum gate instructions, a quantum simulator that emulates these instructions on a classical device, and a software controller that sends analog signals to a very expensive quantum hardware based on quantum circuits. In comparison to traditional compilers and architecture simulators, QSSes are difficult to tests due to the probabilistic nature of results, the lack of clear hardware specifications, and quantum programming complexity.This work devises a novel differential testing approach for QSSes, named QDiff with three major innovations: (1) We generate input programs to be tested via semantics-preserving, source to source transformation to explore program variants. (2) We speed up differential testing by filtering out quantum circuits that are not worthwhile to execute on quantum hardware by analyzing static characteristics such as a circuit depth, 2-gate operations, gate error rates, and T1 relaxation time. (3) We design an extensible equivalence checking mechanism via distribution comparison functions such as Kolmogorov–Smirnov test and cross entropy.We evaluate QDiff with three widely-used open source QSSes: Qiskit from IBM, Cirq from Google, and Pyquil from Rigetti. By running QDiff on both real hardware and quantum simulators, we found several critical bugs revealing potential instabilities in these platforms. QDiff's source transformation is effective in producing semantically equivalent yet not-identical circuits (i.e., 34% of trials), and its filtering mechanism can speed up differential testing by 66%.

Background: Quantum machine learning (QML) holds significant promise for advancing medical image classification. However, its practical application to large-scale, high-resolution datasets is constrained by the limited number of qubits and the inherent noise in current quantum hardware. Methods: In this study, we propose the Fused Quantum Dual-Backbone Network (FQDN), a novel hybrid architecture that integrates classical convolutional neural networks (CNNs) with quantum circuits. This design is optimized for the noisy intermediate-scale quantum (NISQ), enabling efficient computation despite hardware limitations. We evaluate FQDN on the task of gastrointestinal (GI) disease classification using wireless capsule endoscopy (WCE) images. Results: The proposed model achieves a substantial reduction in parameter complexity, with a 29.04% decrease in total parameters and a 94.44% reduction in trainable parameters, while outperforming its classical counterpart. FQDN achieves an accuracy of 95.80% on the validation set and 95.42% on the test set. Conclusions: These results demonstrate the potential of QML to enhance diagnostic accuracy in medical imaging.

<sec><p indent="0mm">To overcome longstanding issues of error propagation and low computational efficiency in geographical information systems (GIS) and computer-aided design (CAD) systems, high-accuracy surface modeling (HASM) methods were developed through the systematic integration of systems theory, optimization cybernetics, and surface theory. Following nearly two decades of numerical experimentation and empirical investigation, a universal fundamental theorem of surface modeling (UFTSM) was formulated. This theorem provides a general theoretical framework applicable to spatial interpolation, upscaling, downscaling, data fusion, and model–data assimilation across a wide range of disciplines, including Earth surface system science, eco-environmental informatics, medical imaging, and computer-aided design. </sec><sec> The UFTSM was first successfully applied to the simulation of eco-environmental surfaces. Within the conceptual framework of the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES), eco-environmental components were classified into three categories: nature (including species diversity, ecosystem structure, and geographical features), nature’s contributions to people (such as food provision, freshwater supply, and environmental pollution remediation), and drivers of natural change (including climate change, land-use change, policies, and regulations). The term eco-environmental surface is used as a unified concept to represent surfaces describing nature, nature’s contributions to people, or drivers of natural change. Numerous studies have demonstrated that intrinsic information (e.g., ground-based observations) and extrinsic information (e.g., satellite observations) provide complementary perspectives, and that neither alone can fully characterize an eco-environmental surface. Instead, such surfaces are governed by the joint influence of intrinsic and extrinsic information, and cannot be adequately understood without considering both. To address the challenge of simulating eco-environmental surfaces through the integration of these two information sources, an iterative differential method for HASM-based machine learning was developed, and a fundamental theorem for eco-environmental surface modeling (FTEEM) was proposed. In addition, a suite of high-efficiency algorithms suitable for classical computing platforms, including a modified conjugate gradient algorithm, a multigrid algorithm, an adaptation algorithm, and adjustment computation, was designed to accelerate eco-environmental surface modeling. Compared with existing surface modeling approaches, HASM-based applications exhibit substantially improved accuracy. However, computational cost remains a major bottleneck for global-scale eco-environmental surface modeling, particularly as spatial resolution becomes increasingly fine. </sec><sec> To address the limitations of classical algorithms and hardware, HASM was reformulated as a large sparse linear system using the Lagrange multiplier method. This system was then implemented on both a real quantum computer and a virtual quantum computing platform by employing two widely used quantum linear solvers: the Harrow-Hassidim-Lloyd (HHL) algorithm and the iterative refinement of the variational quantum linear solver (iVQLS). Based on these approaches, two HASM-oriented quantum linear solvers, HASM-HHL and HASM-iVQLS, were developed, enabling the solution of simulation problems that are intractable for classical computers. The respective advantages and limitations of HASM-HHL and HASM-iVQLS, as quantum machine learning algorithms, were systematically evaluated through simulation experiments conducted on both real and virtual quantum computing platforms. The comparative results highlight the urgent need for a universal tool library that supports both classical and quantum intelligent computing. Moreover, the development of a full-stack quantum input–computing–output system is essential for overcoming the principal challenges currently faced by HASM-based quantum machine learning. </sec>

Quantum Machine Learning (QML) is an emerging interdisciplinary field that integrates quantum computing with classical machine learning techniques to enhance computational efficiency and solve complex problems beyond the capabilities of classical systems. This paper explores fundamental QML algorithms, including quantum-enhanced data processing, quantum neural networks, and quantum support vector machines. We discuss how quantum speedup can be achieved through quantum parallelism and entanglement, leading to improvements in optimization and data classification tasks. Additionally, we highlight applications of QML in areas such as drug discovery, financial modeling, and cryptography. While current quantum hardware imposes limitations, ongoing advancements in quantum algorithms and error correction techniques suggest a promising future for QML. We conclude with a discussion on the challenges and future directions in the field, emphasizing the need for hybrid quantum-classical approaches and scalable quantum hardware.

In the current noisy intermediate-scale quantum (NISQ)era, quantum machine learning is emerging as a dominant paradigm to program gate-based quantum computers. In quantum machine learning, the gates of a quantum circuit are parameterized, and the parameters are tuned via classical optimization based on data and on measurements of the outputs of the circuit. Parameterized quantum circuits (PQCs) can efficiently address combinatorial optimization problems, implement probabilistic generative models, and carry out inference (classification and regression). This monograph provides a self-contained introduction to quantum machine learning for an audience of engineers with a back groundin probability and linear algebra. It first describes the necessary background, concepts, and tools necessary to describe quantum operations and measurements. Then,it covers parameterized quantum circuits, the variation alquantum eigensolver, as well as unsupervised and supervised quantum machine learning formulations.