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

IntechOpen eBooks

Quantum Neural Machine Learning: Theory and Experiments

Carlos Pedro Gonçalves

Published Feb 12, 2019• 13 citations
Publisher

Abstract

Cloud-based access to quantum computers opens up the way for the empirical implementation of quantum artificial neural networks and for the future integration of quantum computation in different devices, using the cloud to access a quantum computer. The current work experimentally implements quantum artificial neural networks on IBM’s quantum computers, accessed via cloud. Examples are provided for the XOR Boolean function representation problem and decision under risk; in the last case, quantum object-oriented programming using IBM’s Qiskit Python library is employed to implement a form of quantum neural reinforcement learning applied to a classical decision under risk problem, showing how decision can be integrated into a quantum artificial intelligence system, where an artificial agent learns how to select an optimal action when facing a classical gamble. A final reflection is provided on quantum robotics and a future where robotic systems are connected to quantum computers via cloud, using quantum neural computation to learn to optimize tasks and act accordingly.

DOI
10.5772/intechopen.84149

Related papers

Quantum Robotics, Neural Networks and the Quantum Force Interpretation

Carlos Pedro Gonçalves

A future quantum technological infrastructure demands the development of quantum cyber-physical-cognitive systems, merging quantum artificial intelligence, quantum robotics and quantum information and communication technologies. To support such a development, the current work introduces a new interpretation of quantum mechanics, grounded on a link between quantum computer science, systems science and field-based computation. This new interpretation is applied to quantum artificial neural networks, with examples implemented experimentally on IBM's five qubit transmon bowtie chip, accessed via cloud using IBM Q Experience, illustrating how quantum neural computing can be implemented on actual quantum computers. A new form of quantum neural machine learning, based on a quantum optimization of a conditional utility function is also introduced and applied to quantum robotics, where a quantum robot, characterized by an interface and a multilayer quantum artificial neural network, interacts with a quantum target, changing the target's dynamics adaptively, based upon the quantum optimization dynamics, computing the optima for a performance measure and changing the target's dynamics accordingly.

NeuroQuantology•Jan 1, 2019•3 citations

Bridging Quantum and Classical AI: Cloud-Based Quantum Computing for Machine Learning

Chandrakanth Puligundla

The convergence of artificial intelligence (AI), quantum computing, and cloud infrastructure represents a paradigm shift in how intelligent systems are designed, trained, and deployed. As AI models continue to demand exponential computational resources, classical systems are increasingly reaching their performance limits in domains such as high-dimensional optimization, complex pattern recognition, and probabilistic modeling. Quantum computing, with its foundational principles of superposition, entanglement, and quantum parallelism, offers a theoretical edge in solving problems that are intractable for conventional hardware. However, the practical deployment of quantum algorithms—particularly those relevant to machine learning (ML) has been hindered by the limited scalability and accessibility of quantum hardware. To bridge this gap, cloud-based quantum computing platforms have emerged, providing remote, programmable access to quantum devices and hybrid runtimes. In this context, the present study offers a comprehensive review of cloud-delivered quantum AI systems, examining core architectures, hybrid quantum-classical algorithms, platform capabilities, and real-world use cases. The paper synthesizes recent advances and performance insights from systems such as Amazon Braket, IBM Quantum, and Azure Quantum, while critically analyzing algorithmic trends like variational quantum circuits and quantum kernel methods. It further explores challenges including circuit depth limitations, latency in hybrid models, and standardization barriers across toolchains. By consolidating current research and implementation patterns, this review aims to inform the design and future trajectory of scalable, cloud-native quantum AI applications.

IEEE International Symposium on Technology and Society (ISTAS)•Sep 10, 2025•1 citation

Quantum Neural Networks

Artyom M. Grigoryan, Sos S. Agaian

Quantum neural networks (QNNs) are a burgeoning field that merges the principles of quantum mechanics with machine learning. These models aim to leverage the unique capabilities of quantum computers, such as superposition, entanglement, and interference, to overcome limitations faced by classical neural networks (NNs). Quantum machine learning algorithms often produce probabilistic results and contain correlated components. This chapter explores a general method for building NNs inspired by classical architectures on quantum computers. It delves into the key differences and similarities between quantum and classical NNs and also explores the potential of quantum-classical hybrid approaches. The chapter also discusses some potential applications and future trends in the exciting field of QNNs. Artificial neurons are the building blocks of artificial neural network (ANN). Reinforcement learning is a powerful branch of machine learning where agents learn to make optimal decisions through a feedback mechanism of rewards and penalties.

Wiley eBooks•Feb 10, 2025•1 citation

Exploring Quantum Neural Networks: Enhancing AI with Quantum Computing Power

Eleanor WHITMORE

A promising combination of artificial intelligence and quantum computing, quantum neural networks (QNNs) have the potential to completely transform the way neural networks interpret and learn from data. QNNs can outperform classical neural networks in terms of speed, efficiency, and scalability by utilizing the special qualities of quantum physics, such as superposition, entanglement, and quantum parallelism. The basic ideas of QNNs, their structures, and the ways in which quantum algorithms can be incorporated into machine learning processes to improve problem-solving skills are all examined in this study. current developments in QNNs, emphasizing how they can be used for challenging applications including pattern recognition, optimization, and high-dimensional data space decision-making. We also go over the difficulties in creating scalable QNN models and the possible future applications of QNNs in artificial intelligence. By utilizing the potential of quantum computing, QNNs have the potential to advance artificial intelligence by providing answers to issues that are now intractable through traditional methods.

The Sankalpa: International Journal of Management Decisions•Jun 28, 2026•0 citations

Artificial Intelligence and Machine Learning Algorithms in Quantum Computing Domain

Syed Abdul Moeed, P. Niranjan, G. Ashmitha

Quantum information and artificial learning systems, for example, are cutting-edge technologies that could have a significant impact on our civilization in the future. The difficulties and challenges associated with quantum information, for example, differ significantly from those associated with artificial intelligence, machine learning, and other related fields. These issues have mostly been tackled separately until now. Many researchers are beginning to wonder whether or not these professions can learn from one another. Quantum computing theory is exploding right now, as is the classical machine learning theory of learning from experience. Researchers have recently looked into the possibility that quantum computing could aid in the improvement of current machine learning methods. Hybrid quantum machine learning makes use of quantum physics as well as classical and quantum algorithms. Quantum procedures, rather than classical data, can be used to analyze quantum states. Quantum algorithms, on the other hand, have the potential to improve classical data science techniques by an order of magnitude. We'll go over the fundamental concepts of quantum machine learning right now. The methods we offer combine classical machine learning algorithms with quantum computing techniques. Using IBM's quantum processor, this paper demonstrates how to implement a multiclass tree tensor network. We also present a quantum tomography problem method based on neural networks. It is possible for us to forecast the quantum state without taking noise into account thanks to our tomography technology. In many investigations, a classical-quantum technique can uncover latent dependence between input data and output measurement results.

Wiley eBooks•May 29, 2023•1 citation

Quantum implementation of an artificial feed-forward neural network

Francesco Tacchino, Panagiotis Kl. Barkoutsos, Chiara Macchiavello +3 more

Abstract Artificial intelligence algorithms largely build on multi-layered neural networks. Coping with their increasing complexity and memory requirements calls for a paradigmatic change in the way these powerful algorithms are run. Quantum computing promises to solve certain tasks much more efficiently than any classical computing machine, and actual quantum processors are now becoming available through cloud access to perform experiments and testing also outside of research labs. Here we show in practice an experimental realization of an artificial feed-forward neural network implemented on a state-of-art superconducting quantum processor using up to 7 active qubits. The network is made of quantum artificial neurons, which individually display a potential advantage in storage capacity with respect to their classical counterpart, and it is able to carry out an elementary classification task which would be impossible to achieve with a single node. We demonstrate that this network can be equivalently operated either via classical control or in a completely coherent fashion, thus opening the way to hybrid as well as fully quantum solutions for artificial intelligence to be run on near-term intermediate-scale quantum hardware.

arXiv:1912.12486•Quantum Science and Technology•Sep 16, 2020•96 citations
Cloud-based access to quantum computers opens up the way for the empirical implementation of quantum artificial neural networks and for the future integration of quantum computation in different devices, using the cloud to access a quantum computer. The current work experimentally implements quantum artificial neural networks on IBM’s quantum computers, accessed via cloud. Examples are provided for the XOR Boolean function representation problem and decision under risk; in the last case, quantum object-oriented programming using IBM’s Qiskit Python library is employed to implement a form of quantum neural reinforcement learning applied to a classical decision under risk problem, showing how decision can be integrated into a quantum artificial intelligence system, where an artificial agent learns how to select an optimal action when facing a classical gamble. A final reflection is provided on quantum robotics and a future where robotic systems are connected to quantum computers via cloud, using quantum neural computation to learn to optimize tasks and act accordingly.
A future quantum technological infrastructure demands the development of quantum cyber-physical-cognitive systems, merging quantum artificial intelligence, quantum robotics and quantum information and communication technologies. To support such a development, the current work introduces a new interpretation of quantum mechanics, grounded on a link between quantum computer science, systems science and field-based computation. This new interpretation is applied to quantum artificial neural networks, with examples implemented experimentally on IBM's five qubit transmon bowtie chip, accessed via cloud using IBM Q Experience, illustrating how quantum neural computing can be implemented on actual quantum computers. A new form of quantum neural machine learning, based on a quantum optimization of a conditional utility function is also introduced and applied to quantum robotics, where a quantum robot, characterized by an interface and a multilayer quantum artificial neural network, interacts with a quantum target, changing the target's dynamics adaptively, based upon the quantum optimization dynamics, computing the optima for a performance measure and changing the target's dynamics accordingly.
The convergence of artificial intelligence (AI), quantum computing, and cloud infrastructure represents a paradigm shift in how intelligent systems are designed, trained, and deployed. As AI models continue to demand exponential computational resources, classical systems are increasingly reaching their performance limits in domains such as high-dimensional optimization, complex pattern recognition, and probabilistic modeling. Quantum computing, with its foundational principles of superposition, entanglement, and quantum parallelism, offers a theoretical edge in solving problems that are intractable for conventional hardware. However, the practical deployment of quantum algorithms—particularly those relevant to machine learning (ML) has been hindered by the limited scalability and accessibility of quantum hardware. To bridge this gap, cloud-based quantum computing platforms have emerged, providing remote, programmable access to quantum devices and hybrid runtimes. In this context, the present study offers a comprehensive review of cloud-delivered quantum AI systems, examining core architectures, hybrid quantum-classical algorithms, platform capabilities, and real-world use cases. The paper synthesizes recent advances and performance insights from systems such as Amazon Braket, IBM Quantum, and Azure Quantum, while critically analyzing algorithmic trends like variational quantum circuits and quantum kernel methods. It further explores challenges including circuit depth limitations, latency in hybrid models, and standardization barriers across toolchains. By consolidating current research and implementation patterns, this review aims to inform the design and future trajectory of scalable, cloud-native quantum AI applications.
Quantum neural networks (QNNs) are a burgeoning field that merges the principles of quantum mechanics with machine learning. These models aim to leverage the unique capabilities of quantum computers, such as superposition, entanglement, and interference, to overcome limitations faced by classical neural networks (NNs). Quantum machine learning algorithms often produce probabilistic results and contain correlated components. This chapter explores a general method for building NNs inspired by classical architectures on quantum computers. It delves into the key differences and similarities between quantum and classical NNs and also explores the potential of quantum-classical hybrid approaches. The chapter also discusses some potential applications and future trends in the exciting field of QNNs. Artificial neurons are the building blocks of artificial neural network (ANN). Reinforcement learning is a powerful branch of machine learning where agents learn to make optimal decisions through a feedback mechanism of rewards and penalties.
A promising combination of artificial intelligence and quantum computing, quantum neural networks (QNNs) have the potential to completely transform the way neural networks interpret and learn from data. QNNs can outperform classical neural networks in terms of speed, efficiency, and scalability by utilizing the special qualities of quantum physics, such as superposition, entanglement, and quantum parallelism. The basic ideas of QNNs, their structures, and the ways in which quantum algorithms can be incorporated into machine learning processes to improve problem-solving skills are all examined in this study. current developments in QNNs, emphasizing how they can be used for challenging applications including pattern recognition, optimization, and high-dimensional data space decision-making. We also go over the difficulties in creating scalable QNN models and the possible future applications of QNNs in artificial intelligence. By utilizing the potential of quantum computing, QNNs have the potential to advance artificial intelligence by providing answers to issues that are now intractable through traditional methods.
Quantum information and artificial learning systems, for example, are cutting-edge technologies that could have a significant impact on our civilization in the future. The difficulties and challenges associated with quantum information, for example, differ significantly from those associated with artificial intelligence, machine learning, and other related fields. These issues have mostly been tackled separately until now. Many researchers are beginning to wonder whether or not these professions can learn from one another. Quantum computing theory is exploding right now, as is the classical machine learning theory of learning from experience. Researchers have recently looked into the possibility that quantum computing could aid in the improvement of current machine learning methods. Hybrid quantum machine learning makes use of quantum physics as well as classical and quantum algorithms. Quantum procedures, rather than classical data, can be used to analyze quantum states. Quantum algorithms, on the other hand, have the potential to improve classical data science techniques by an order of magnitude. We'll go over the fundamental concepts of quantum machine learning right now. The methods we offer combine classical machine learning algorithms with quantum computing techniques. Using IBM's quantum processor, this paper demonstrates how to implement a multiclass tree tensor network. We also present a quantum tomography problem method based on neural networks. It is possible for us to forecast the quantum state without taking noise into account thanks to our tomography technology. In many investigations, a classical-quantum technique can uncover latent dependence between input data and output measurement results.
Abstract Artificial intelligence algorithms largely build on multi-layered neural networks. Coping with their increasing complexity and memory requirements calls for a paradigmatic change in the way these powerful algorithms are run. Quantum computing promises to solve certain tasks much more efficiently than any classical computing machine, and actual quantum processors are now becoming available through cloud access to perform experiments and testing also outside of research labs. Here we show in practice an experimental realization of an artificial feed-forward neural network implemented on a state-of-art superconducting quantum processor using up to 7 active qubits. The network is made of quantum artificial neurons, which individually display a potential advantage in storage capacity with respect to their classical counterpart, and it is able to carry out an elementary classification task which would be impossible to achieve with a single node. We demonstrate that this network can be equivalently operated either via classical control or in a completely coherent fashion, thus opening the way to hybrid as well as fully quantum solutions for artificial intelligence to be run on near-term intermediate-scale quantum hardware.