Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2107.10541 · Machine Learning Science and Technology

Qsun: an open-source platform towards practical quantum machine learning applications

Quoc Chuong Nguyen, Le Bin Ho, Lan Nguyen Tran, Hung Q. Nguyen

Published Mar 1, 2022• 13 citations
arXivHTMLPDF

Abstract

Abstract Currently, quantum hardware is restrained by noises and qubit numbers. Thus, a quantum virtual machine (QVM) that simulates operations of a quantum computer on classical computers is a vital tool for developing and testing quantum algorithms before deploying them on real quantum computers. Various variational quantum algorithms (VQAs) have been proposed and tested on QVMs to surpass the limitations of quantum hardware. Our goal is to exploit further the VQAs towards practical applications of quantum machine learning (QML) using state-of-the-art quantum computers. In this paper, we first introduce a QVM named Qsun, whose operation is underlined by quantum state wavefunctions. The platform provides native tools supporting VQAs. Especially using the parameter-shift rule, we implement quantum differentiable programming essential for gradient-based optimization. We then report two tests representative of QML: quantum linear regression and quantum neural network.

DOI
10.1088/2632-2153/ac5997

Related papers

Quantum Machine Learning: Applications, Algorithms, and Hardware Challenges

Juan Lopez

Quantum Machine Learning (QML) integrates quantum algorithms into machine learning programs to enhance and expedite classical machine learning techniques. It leverages quantum data and hybrid quantum-classical models, utilizing the principles of superposition and entanglement to handle complex joint probability distributions that would require exponential classical computational resources. QML aims to harness the unique properties of quantum computers for practical machine learning tasks, with the goal of achieving quantum advantage over classical approaches. QML finds applications in diverse fields such as chemical and quantum matter simulation, quantum control, quantum communication networks, and quantum metrology. Quantum algorithms can analyze quantum states and improve computational speed and data storage. Two main frameworks, quantum kernel methods and variational quantum algorithms, are widely used due to their implement ability on quantum hardware and capacity to work on general datasets. Quantum computers can solve linear algebraic problems, calculate eigenvectors and eigenvalues, and perform support vector algorithms at exponentially faster rates than classical computers. Despite its potential, QML faces significant challenges related to quantum hardware capabilities, including limited qubit connectivity, noise, coherence times, and errors in state preparation and measurement. Hardware constraints, compatibility issues, high computational and memory requirements, and the difficulty of quantum programming also pose obstacles. Overcoming these hardware and software limitations is crucial for realizing the full potential of quantum machine learning

International Journal of AI BigData Computational and Management Studies•Jan 1, 2024•1 citation

Quantum Machine Learning: Algorithms, Applications, and Limitations

Mohammed Madouri, Olusoji John Samuel

As the limits of classical machine learning (ML) become increasingly evident—especially in terms of computational scalability and data processing—quantum computing emerges as a promising frontier capable of addressing these challenges. Quantum Machine Learning (QML) represents the intersection of quantum computing and traditional ML, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance learning capabilities, accelerate training, and solve complex problems that are intractable for classical algorithms. This paper provides a comprehensive overview of the evolving field of QML, beginning with the theoretical foundations of quantum computing and its synergy with classical machine learning principles. We explore key QML algorithms, including quantum support vector machines (QSVM), variational quantum classifiers (VQC), quantum neural networks (QNN), and hybrid quantum-classical approaches that exemplify the practical integration of both paradigms. We further examine real-world applications of QML across domains such as drug discovery, finance, climate modeling, and optimization, where quantum enhancements have begun to show early but promising results. Despite its theoretical potential, QML faces substantial limitations, including quantum hardware instability, limited qubit scalability, noise sensitivity, and unresolved challenges in quantum data encoding and interpretability. In synthesizing recent advancements and persistent obstacles, this paper highlights the importance of continued interdisciplinary research, algorithmic refinement, and hardware evolution. We also outline future directions that could lead QML from experimental promise to practical utility, including developments in quantum error correction, benchmarking standards, and application-specific quantum architectures

Journal of Science Technology and Engineering Research•Mar 30, 2024•3 citations

Variational Quantum Regression on NISQ Hardware with Error Mitigation

Eider Garate, Paul San Sebastian, Guillermo Valverde +2 more

At the intersection of two promising technologies, Machine Learning (ML) and Quantum Computing (QC), Quantum Machine Learning (QML) emerges. However, while QC is still in an early stage of development, QML is even more so. In this study, the Auto-MPG dataset was selected for its dimension, making it suitable for QML tasks within the current limitations of quantum hardware, especially regarding qubit requirements. Unlike classification problems that dominate the literature, regression problems have only been explored theoretically. This study aims to bridge that gap by applying QML techniques to a practical regression task. To this end, a preliminary analysis was conducted using a classical model as a reference point for subsequent evaluation. The quantum experimentation was performed in two phases: first, the model was trained in an ideal simulator to determine the model's best hyperparameters. Then, these best models were run in a noisy simulator using quantum error mitigation techniques. The results show how the Variational Quantum Algorithms (VQA) outperforms classical Extreme Gradient Boosting and the methods used to mitigate errors in quantum hardware are effective, as they achieve comparable results between the noisy simulator and the perfect simulator. This brings closer the possible applications in NISQ current devices.

Artificial Intelligence Revolutions (AIR)•Oct 30, 2024•3 citations

Quantum Machine Learning

Savo Glisic, Beatriz Lorenzo

This chapter provides a brief description of quantum machine learning (QML) and its correlation with artificial intelligence. It shows how the quantum counterpart of machine learning (ML) is much faster and more efficient than classical ML. In the QML techniques, the chapter develops quantum algorithms to operate the classical algorithms on a quantum computer. The quantum decision tree employs quantum states to create the classifiers used in ML. The current generation of quantum computing technologies calls for quantum algorithms that require a limited number of qubits and quantum gates, and that are robust against errors. The chapter discusses a low-depth variational quantum algorithm for supervised learning. The parameter-shift rule is an approach to evaluating gradients of parameterized quantum circuits on quantum hardware. The chapter introduces a quantum neural network that can represent labeled data – classical or quantum – and be trained by supervised learning.

Wiley eBooks•Feb 14, 2022•3 citations

Quantum Machine Learning: Algorithms and Applications

Adewuyi Michael Oluwanifemi

Quantum machine learning (QML) represents a cutting-edge convergence of quantum computing and artificial intelligence, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance machine learning algorithms. By exploiting the computational advantages of quantum systems, QML offers the potential for exponential speedups in data processing, optimization, and pattern recognition tasks, particularly for high-dimensional and complex datasets. This article explores the foundational principles, algorithmic approaches, and practical applications of quantum machine learning across domains including finance, chemistry, drug discovery, optimization, and natural language processing. It discusses quantum-enhanced supervised and unsupervised learning, quantum neural networks, variational quantum algorithms, and hybrid quantum-classical architectures. Additionally, the article addresses challenges related to hardware limitations, noise, scalability, and interpretability, as well as the emerging trends in near-term quantum devices, quantum simulators, and integration with classical AI pipelines. Quantum machine learning holds the promise of revolutionizing computational intelligence, offering transformative capabilities for solving problems that are currently intractable for classical systems.

International Journal of Advance Industrial Engineering•Jun 30, 2024•0 citations

Revolutionizing Learning with Qubits

Shatakshi Bhusari, Aniket Badakh, Kalyani Daine +2 more

As the synergy between quantum computing and machine learning unfolds, the paradigm shift brought by QML (Quantum Machine Learning) stands at the forefront of transformative advancements. From quantum-enhanced optimization algorithms to innovative approaches in quantum data representation, the breadth of QML techniques. Special attention is devoted to the emerging field of QNN (Quantum Neural Networks), QSVM (Quantum Support Vector Machines), and the application of quantum computing in enhancing classical machine learning workflows. The practical implications and challenges associated with implementing QML on existing quantum hardware are thoroughly examined, shedding light on the current state and future prospects of scalable quantum machine learning solutions. The paper addresses the intricacies of adapting classical machine learning algorithms to the quantum realm and emphasizes the need for error correction in quantum mechanisms to guarantee quantum results reliability also an extensive examination of the current state of Quantum Machine Learning (QML), emphasizing both the remarkable advancements and the persistent challenges within this burgeoning interdisciplinary field. The primary objectives include synthesizing the latest research findings, offering insights into the practical applications and potential impact of QML, and identifying areas requiring further exploration and development.

Wiley eBooks•Feb 7, 2025•2 citations
Abstract Currently, quantum hardware is restrained by noises and qubit numbers. Thus, a quantum virtual machine (QVM) that simulates operations of a quantum computer on classical computers is a vital tool for developing and testing quantum algorithms before deploying them on real quantum computers. Various variational quantum algorithms (VQAs) have been proposed and tested on QVMs to surpass the limitations of quantum hardware. Our goal is to exploit further the VQAs towards practical applications of quantum machine learning (QML) using state-of-the-art quantum computers. In this paper, we first introduce a QVM named Qsun, whose operation is underlined by quantum state wavefunctions. The platform provides native tools supporting VQAs. Especially using the parameter-shift rule, we implement quantum differentiable programming essential for gradient-based optimization. We then report two tests representative of QML: quantum linear regression and quantum neural network.
Quantum Machine Learning (QML) integrates quantum algorithms into machine learning programs to enhance and expedite classical machine learning techniques. It leverages quantum data and hybrid quantum-classical models, utilizing the principles of superposition and entanglement to handle complex joint probability distributions that would require exponential classical computational resources. QML aims to harness the unique properties of quantum computers for practical machine learning tasks, with the goal of achieving quantum advantage over classical approaches. QML finds applications in diverse fields such as chemical and quantum matter simulation, quantum control, quantum communication networks, and quantum metrology. Quantum algorithms can analyze quantum states and improve computational speed and data storage. Two main frameworks, quantum kernel methods and variational quantum algorithms, are widely used due to their implement ability on quantum hardware and capacity to work on general datasets. Quantum computers can solve linear algebraic problems, calculate eigenvectors and eigenvalues, and perform support vector algorithms at exponentially faster rates than classical computers. Despite its potential, QML faces significant challenges related to quantum hardware capabilities, including limited qubit connectivity, noise, coherence times, and errors in state preparation and measurement. Hardware constraints, compatibility issues, high computational and memory requirements, and the difficulty of quantum programming also pose obstacles. Overcoming these hardware and software limitations is crucial for realizing the full potential of quantum machine learning
As the limits of classical machine learning (ML) become increasingly evident—especially in terms of computational scalability and data processing—quantum computing emerges as a promising frontier capable of addressing these challenges. Quantum Machine Learning (QML) represents the intersection of quantum computing and traditional ML, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance learning capabilities, accelerate training, and solve complex problems that are intractable for classical algorithms. This paper provides a comprehensive overview of the evolving field of QML, beginning with the theoretical foundations of quantum computing and its synergy with classical machine learning principles. We explore key QML algorithms, including quantum support vector machines (QSVM), variational quantum classifiers (VQC), quantum neural networks (QNN), and hybrid quantum-classical approaches that exemplify the practical integration of both paradigms. We further examine real-world applications of QML across domains such as drug discovery, finance, climate modeling, and optimization, where quantum enhancements have begun to show early but promising results. Despite its theoretical potential, QML faces substantial limitations, including quantum hardware instability, limited qubit scalability, noise sensitivity, and unresolved challenges in quantum data encoding and interpretability. In synthesizing recent advancements and persistent obstacles, this paper highlights the importance of continued interdisciplinary research, algorithmic refinement, and hardware evolution. We also outline future directions that could lead QML from experimental promise to practical utility, including developments in quantum error correction, benchmarking standards, and application-specific quantum architectures
At the intersection of two promising technologies, Machine Learning (ML) and Quantum Computing (QC), Quantum Machine Learning (QML) emerges. However, while QC is still in an early stage of development, QML is even more so. In this study, the Auto-MPG dataset was selected for its dimension, making it suitable for QML tasks within the current limitations of quantum hardware, especially regarding qubit requirements. Unlike classification problems that dominate the literature, regression problems have only been explored theoretically. This study aims to bridge that gap by applying QML techniques to a practical regression task. To this end, a preliminary analysis was conducted using a classical model as a reference point for subsequent evaluation. The quantum experimentation was performed in two phases: first, the model was trained in an ideal simulator to determine the model's best hyperparameters. Then, these best models were run in a noisy simulator using quantum error mitigation techniques. The results show how the Variational Quantum Algorithms (VQA) outperforms classical Extreme Gradient Boosting and the methods used to mitigate errors in quantum hardware are effective, as they achieve comparable results between the noisy simulator and the perfect simulator. This brings closer the possible applications in NISQ current devices.
This chapter provides a brief description of quantum machine learning (QML) and its correlation with artificial intelligence. It shows how the quantum counterpart of machine learning (ML) is much faster and more efficient than classical ML. In the QML techniques, the chapter develops quantum algorithms to operate the classical algorithms on a quantum computer. The quantum decision tree employs quantum states to create the classifiers used in ML. The current generation of quantum computing technologies calls for quantum algorithms that require a limited number of qubits and quantum gates, and that are robust against errors. The chapter discusses a low-depth variational quantum algorithm for supervised learning. The parameter-shift rule is an approach to evaluating gradients of parameterized quantum circuits on quantum hardware. The chapter introduces a quantum neural network that can represent labeled data – classical or quantum – and be trained by supervised learning.
Quantum machine learning (QML) represents a cutting-edge convergence of quantum computing and artificial intelligence, aiming to leverage quantum phenomena such as superposition, entanglement, and quantum parallelism to enhance machine learning algorithms. By exploiting the computational advantages of quantum systems, QML offers the potential for exponential speedups in data processing, optimization, and pattern recognition tasks, particularly for high-dimensional and complex datasets. This article explores the foundational principles, algorithmic approaches, and practical applications of quantum machine learning across domains including finance, chemistry, drug discovery, optimization, and natural language processing. It discusses quantum-enhanced supervised and unsupervised learning, quantum neural networks, variational quantum algorithms, and hybrid quantum-classical architectures. Additionally, the article addresses challenges related to hardware limitations, noise, scalability, and interpretability, as well as the emerging trends in near-term quantum devices, quantum simulators, and integration with classical AI pipelines. Quantum machine learning holds the promise of revolutionizing computational intelligence, offering transformative capabilities for solving problems that are currently intractable for classical systems.
As the synergy between quantum computing and machine learning unfolds, the paradigm shift brought by QML (Quantum Machine Learning) stands at the forefront of transformative advancements. From quantum-enhanced optimization algorithms to innovative approaches in quantum data representation, the breadth of QML techniques. Special attention is devoted to the emerging field of QNN (Quantum Neural Networks), QSVM (Quantum Support Vector Machines), and the application of quantum computing in enhancing classical machine learning workflows. The practical implications and challenges associated with implementing QML on existing quantum hardware are thoroughly examined, shedding light on the current state and future prospects of scalable quantum machine learning solutions. The paper addresses the intricacies of adapting classical machine learning algorithms to the quantum realm and emphasizes the need for error correction in quantum mechanisms to guarantee quantum results reliability also an extensive examination of the current state of Quantum Machine Learning (QML), emphasizing both the remarkable advancements and the persistent challenges within this burgeoning interdisciplinary field. The primary objectives include synthesizing the latest research findings, offering insights into the practical applications and potential impact of QML, and identifying areas requiring further exploration and development.