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:1412.3646

Quantum computing for pattern classification

Maria Schuld, Ilya Sinayskiy, Francesco Petruccione

Published Dec 11, 2014• 8 citations
arXivHTMLPDF

Abstract

It is well known that for certain tasks, quantum computing outperforms classical computing. A growing number of contributions try to use this advantage in order to improve or extend classical machine learning algorithms by methods of quantum information theory. This paper gives a brief introduction into quantum machine learning using the example of pattern classification. We introduce a quantum pattern classification algorithm that draws on Trugenberger's proposal for measuring the Hamming distance on a quantum computer (CA Trugenberger, Phys Rev Let 87, 2001) and discuss its advantages using handwritten digit recognition as from the MNIST database.

DOI
10.48550/arxiv.1412.3646

Related papers

An introduction to quantum machine learning

Maria Schuld, Ilya Sinayskiy, Francesco Petruccione

Machine learning algorithms learn a desired input-output relation from examples in order to interpret new inputs. This is important for tasks such as image and speech recognition or strategy optimisation, with growing applications in the IT industry. In the last couple of years, researchers investigated if quantum computing can help to improve classical machine learning algorithms. Ideas range from running computationally costly algorithms or their subroutines efficiently on a quantum computer to the translation of stochastic methods into the language of quantum theory. This contribution gives a systematic overview of the emerging field of quantum machine learning. It presents the approaches as well as technical details in an accessible way, and discusses the potential of a future theory of quantum learning.

arXiv:1409.3097•Contemporary Physics•Oct 15, 2014•1,567 citations

Quantum machine learning for supervised pattern recognition.

Maria Schuld

Humans are experts at recognising patterns in past experience and applying them to new tasks. \nFor example, after seeing pictures of a face we can usually tell if another image contains the \nsame person or not. Machine learning is a research discipline at the intersection of computer \nscience, statistics and mathematics that investigates how pattern recognition can be performed \nby machines and for large amounts of data. Since a few years machine learning has come \ninto the focus of quantum computing in which information processing based on the laws of \nquantum theory is explored. Although large scale quantum computers are still in the first stages \nof development, their theoretical description is well-understood and can be used to formulate \n`quantum software' or `quantum algorithms' for pattern recognition. Researchers can therefore \nanalyse the impact quantum computers may have on intelligent data mining. This approach is \npart of the emerging research discipline of quantum machine learning that harvests synergies \nbetween quantum computing and machine learning. \nThe research objective of this thesis is to understand how we can solve a slightly more specific \nproblem called supervised pattern recognition based on the language that has been developed \nfor universal quantum computers. The contribution it makes is twofold: First, it presents a \nmethodology that understands quantum machine learning as the combination of data encoding into \nquantum systems and quantum optimisation. Second, it proposes several quantum algorithms for \nsupervised pattern recognition. These include algorithms for convex and non-convex optimisation, \nimplementations of distance-based methods through quantum interference, and the preparation of \nquantum states from which solutions can be derived via sampling. Amongst the machine learning \nmethods considered are least-squares linear regression, gradient descent and Newton's method, \nk-nearest neighbour, neural networks as well as ensemble methods. Together with the growing \nbody of literature, this thesis demonstrates that quantum computing offers a number of interesting \ntools for machine learning applications, and has the potential to create new models of how to learn \nfrom data.

•Jan 1, 2017•5 citations

QUANTUM MACHINE LEARNING

Amrit Raj, Jayakumar. Vaithiyashankar, Vishal Kaushik, Sathyaprakash Palaniyappan

Quantum machine learning, a cutting-edge topic of study, brings together the frontiers of quantum computing with classical machine learning. Quantum computing and machine learning may be able to help solve problems in each other's fields of expertise. Due to the surge of new data, there is growing fear that current machine learning algorithms may be exceeding their computational constraints. Thus, in certain machine learning tasks, quantum computing can be an advantage. Quantum machine learning research focuses on the creation and deployment of quantum software that could speed up machine learning in comparison to standard computing systems. Because of improvements in computing power and algorithmic innovation, machine learning approaches have emerged as powerful tools for detecting patterns in data. Because quantum systems exhibit unusual patterns that classical systems are unable to produce efficiently, it is plausible to assume that quantum computers will outperform classical computers on machine learning tasks. The following is a summary of the current state of quantum machine learning research.

•Jul 7, 2022•0 citations

The Use of Quantum Algorithms vs. Classical Algorithms in Machine Learning

Elina Saarikoski

Through the utilization of quantum phenomena to carry out computations that are beyond the capabilities of classical computers, quantum computing has the potential to revolutionize a variety of industries, including machine learning. In this research, we give a comparative study of conventional and quantum algorithms in the context of machine learning, and we compare and contrast the two types of algorithms. The advantages of quantum algorithms, such as quantum parallelism and entanglement, as well as their potential to outperform classical algorithms in tasks such as classification, clustering, and optimization, are investigated in this article. We explain the merits and limitations of quantum machine learning algorithms by means of theoretical analysis and practical tests. We also emphasize the possibility of these algorithms to achieve quantum advantage in certain scenarios. In addition, we examine the difficulties and opportunities associated with incorporating quantum computing into machine learning pipelines, and we describe potential future research objectives in this rapidly developing subject.

Package Printing•Aug 3, 2026•0 citations

Quantum Advantage in Machine Learning: A Comparative Study of Quantum and Classical Algorithms

Ramesh

Quantum computing holds the promise of revolutionizing various fields, including machine learning, by leveraging quantum phenomena to perform computations beyond the capabilities of classical computers. In this paper, we present a comparative study of quantum and classical algorithms in the context of machine learning tasks. We examine the advantages of quantum algorithms, such as quantum parallelism and entanglement, and their potential to outperform classical algorithms in tasks such as classification, clustering, and optimization. Through theoretical analysis and empirical experiments, we demonstrate the strengths and limitations of quantum machine learning algorithms, highlighting their potential for achieving quantum advantage in certain scenarios. Additionally, we discuss the challenges and opportunities for integrating quantum computing into machine learning pipelines and outline future research directions in this rapidly evolving field.

Journal of Quantum Science and Technology.•Mar 31, 2024•0 citations

QUANTUM COMPUTING AND QUANTUM MACHINE LEARNING

Ashok Kumar, Manoj Kumar Gupta, Shyam Lal

Quantum machine learning lies at the intersection of quantum computing and classical machine learning, two rapidly advancing research fields. As the data required for classical models continues to grow, quantum computing offers a solution by handling large datasets more efficiently and potentially accelerating learning algorithms. Unlike classical systems, quantum systems generate unique patterns, suggesting that quantum computers may surpass classical ones in machine learning tasks. This paper reviews the current literature on quantum machine learning and its potential advantages in run time, capacity, and learning efficiency. Examples include quantum-enhanced models such as the hybrid Helmholtz machine, which improves run time through quantum sampling, and quantum neural networks, which offer increased capacity and better learning efficiency.

Iterative International Publishers eBooks•Jun 5, 2025•2 citations
It is well known that for certain tasks, quantum computing outperforms classical computing. A growing number of contributions try to use this advantage in order to improve or extend classical machine learning algorithms by methods of quantum information theory. This paper gives a brief introduction into quantum machine learning using the example of pattern classification. We introduce a quantum pattern classification algorithm that draws on Trugenberger's proposal for measuring the Hamming distance on a quantum computer (CA Trugenberger, Phys Rev Let 87, 2001) and discuss its advantages using handwritten digit recognition as from the MNIST database.
Machine learning algorithms learn a desired input-output relation from examples in order to interpret new inputs. This is important for tasks such as image and speech recognition or strategy optimisation, with growing applications in the IT industry. In the last couple of years, researchers investigated if quantum computing can help to improve classical machine learning algorithms. Ideas range from running computationally costly algorithms or their subroutines efficiently on a quantum computer to the translation of stochastic methods into the language of quantum theory. This contribution gives a systematic overview of the emerging field of quantum machine learning. It presents the approaches as well as technical details in an accessible way, and discusses the potential of a future theory of quantum learning.
Humans are experts at recognising patterns in past experience and applying them to new tasks. \nFor example, after seeing pictures of a face we can usually tell if another image contains the \nsame person or not. Machine learning is a research discipline at the intersection of computer \nscience, statistics and mathematics that investigates how pattern recognition can be performed \nby machines and for large amounts of data. Since a few years machine learning has come \ninto the focus of quantum computing in which information processing based on the laws of \nquantum theory is explored. Although large scale quantum computers are still in the first stages \nof development, their theoretical description is well-understood and can be used to formulate \n`quantum software' or `quantum algorithms' for pattern recognition. Researchers can therefore \nanalyse the impact quantum computers may have on intelligent data mining. This approach is \npart of the emerging research discipline of quantum machine learning that harvests synergies \nbetween quantum computing and machine learning. \nThe research objective of this thesis is to understand how we can solve a slightly more specific \nproblem called supervised pattern recognition based on the language that has been developed \nfor universal quantum computers. The contribution it makes is twofold: First, it presents a \nmethodology that understands quantum machine learning as the combination of data encoding into \nquantum systems and quantum optimisation. Second, it proposes several quantum algorithms for \nsupervised pattern recognition. These include algorithms for convex and non-convex optimisation, \nimplementations of distance-based methods through quantum interference, and the preparation of \nquantum states from which solutions can be derived via sampling. Amongst the machine learning \nmethods considered are least-squares linear regression, gradient descent and Newton's method, \nk-nearest neighbour, neural networks as well as ensemble methods. Together with the growing \nbody of literature, this thesis demonstrates that quantum computing offers a number of interesting \ntools for machine learning applications, and has the potential to create new models of how to learn \nfrom data.
Quantum machine learning, a cutting-edge topic of study, brings together the frontiers of quantum computing with classical machine learning. Quantum computing and machine learning may be able to help solve problems in each other's fields of expertise. Due to the surge of new data, there is growing fear that current machine learning algorithms may be exceeding their computational constraints. Thus, in certain machine learning tasks, quantum computing can be an advantage. Quantum machine learning research focuses on the creation and deployment of quantum software that could speed up machine learning in comparison to standard computing systems. Because of improvements in computing power and algorithmic innovation, machine learning approaches have emerged as powerful tools for detecting patterns in data. Because quantum systems exhibit unusual patterns that classical systems are unable to produce efficiently, it is plausible to assume that quantum computers will outperform classical computers on machine learning tasks. The following is a summary of the current state of quantum machine learning research.
Through the utilization of quantum phenomena to carry out computations that are beyond the capabilities of classical computers, quantum computing has the potential to revolutionize a variety of industries, including machine learning. In this research, we give a comparative study of conventional and quantum algorithms in the context of machine learning, and we compare and contrast the two types of algorithms. The advantages of quantum algorithms, such as quantum parallelism and entanglement, as well as their potential to outperform classical algorithms in tasks such as classification, clustering, and optimization, are investigated in this article. We explain the merits and limitations of quantum machine learning algorithms by means of theoretical analysis and practical tests. We also emphasize the possibility of these algorithms to achieve quantum advantage in certain scenarios. In addition, we examine the difficulties and opportunities associated with incorporating quantum computing into machine learning pipelines, and we describe potential future research objectives in this rapidly developing subject.
Quantum computing holds the promise of revolutionizing various fields, including machine learning, by leveraging quantum phenomena to perform computations beyond the capabilities of classical computers. In this paper, we present a comparative study of quantum and classical algorithms in the context of machine learning tasks. We examine the advantages of quantum algorithms, such as quantum parallelism and entanglement, and their potential to outperform classical algorithms in tasks such as classification, clustering, and optimization. Through theoretical analysis and empirical experiments, we demonstrate the strengths and limitations of quantum machine learning algorithms, highlighting their potential for achieving quantum advantage in certain scenarios. Additionally, we discuss the challenges and opportunities for integrating quantum computing into machine learning pipelines and outline future research directions in this rapidly evolving field.
Quantum machine learning lies at the intersection of quantum computing and classical machine learning, two rapidly advancing research fields. As the data required for classical models continues to grow, quantum computing offers a solution by handling large datasets more efficiently and potentially accelerating learning algorithms. Unlike classical systems, quantum systems generate unique patterns, suggesting that quantum computers may surpass classical ones in machine learning tasks. This paper reviews the current literature on quantum machine learning and its potential advantages in run time, capacity, and learning efficiency. Examples include quantum-enhanced models such as the hybrid Helmholtz machine, which improves run time through quantum sampling, and quantum neural networks, which offer increased capacity and better learning efficiency.