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

Informatization and communication

Research and development of quantum neural networks, their effective dimension and trainability

S.M. Gushansky, V.S. Potapov

Published Jan 1, 2022• 0 citations
Publisher

Abstract

Over the past few decades, there has been a significant breakthrough in the field of quantum computing. Research is of growing interest, which has recently led to the development of quantum information systems prototypes and methods for their development. The paper describes the possibilities, advantages and disadvantages of quantum neural networks. The analysis of throughput, learning complexity and comparison of a classical feed-forward neural network and a quantum neural network with two different feature maps is performed.

DOI
10.34219/2078-8320-2022-13-2-7-11

Related papers

Research of Implementation Methods for Quantum Machine Learning and Their Development on QPU

Viktor Potapov, Sergey M. Gushanskiy

Over the past few decades, there has been a significant breakthrough in the field of quantum computing. Research is of growing interest, which has recently led to the development of quantum information systems prototypes and methods for their development. The paper describes the possibilities, advantages and disadvantages of quantum neural networks. The analysis of throughput, learning complexity and comparison of a classical feed-forward neural network and a quantum neural network with two different feature maps is carried out.

Panhellenic Conference on Informatics•Nov 25, 2022•0 citations

Overview of Quantum Computing in Quantum Neural Network and Artificial Intelligence

M. Vasuki, A. Karunamurthy, R. Ramakrishnan +1 more

In recent years, quantum computing has emerged as a potentially gamechanging technology, with applications across various disciplines, including AI and machine learning.In recent years, the combination of quantum computing and neural networks has led to the development of quantum neural networks (QNNs).This paper explores the potential of QNNs and their applications in solving complex problems that are challenging for classical neural networks.This paper explores the fundamental principles of quantum computing, the architecture of QNNs, and their advantages over classical neural networks.Furthermore, this will highlight key research areas and challenges in the development and utilization of QNNs.Through an in-depth analysis, it demonstrates the QNNs hold significant promise for addressing complex computational problems and advancing the field of artificial intelligence.

Quing International Journal of Innovative Research in Science and Engineering•Jun 30, 2023•3 citations

A Comparative Study of Classical and Quantum Neural Networks

Chenhui Zhao

In recent years, classical neural networks have been widely used in various applications and have achieved remarkable success. However, with the advent of quantum computing, there is a growing interest in quantum neural networks (QNNs) as a potential alternative to classical machine learning. In this thesis, we study the architectures of quantum and classical neural networks. We also investigate the performance of QNNs compared to classical neural networks from various aspects, such as vanishing gradient, trainability, expressivity. Our experiments demonstrate that QNNs have the potential to outperform classical neural networks in specific scenarios. While more powerful QNNs exhibit improved performance compared to classical neural networks, our findings also indicate that less powerful QNNs may not always yield significant improvements. This suggests that the effectiveness of QNNs in surpassing classical approaches is contingent on factors such as network architecture, optimization techniques, problem complexity.

Työväentutkimus Vuosikirja•Jan 1, 2023•0 citations

Advances in Quantum Deep Learning: An Overview

Siddhant Garg, Goutham Ramakrishnan

The last few decades have seen significant breakthroughs in the fields of deep learning and quantum computing. Research at the junction of the two fields has garnered an increasing amount of interest, which has led to the development of quantum deep learning and quantum-inspired deep learning techniques in recent times. In this work, we present an overview of advances in the intersection of quantum computing and deep learning by discussing the technical contributions, strengths and similarities of various research works in this domain. To this end, we review and summarise the different schemes proposed to model quantum neural networks (QNNs) and other variants like quantum convolutional networks (QCNNs). We also briefly describe the recent progress in quantum inspired classic deep learning algorithms and their applications to natural language processing.

arXiv:2005.04316•May 8, 2020•49 citations

Research of Quantum Neural Networks and Development of a Single-qubit Model of Neuron

Sergey M. Gushanskiy, Viktor Potapov, Alexey Samoylov

Recently, there has been a rapid increase interest in quantum computers. Their work is based on the use of quantum-mechanical phenomena such as superposition and entanglement for computing to transform input data into outputs, which can actually provide effective performance 3-4 orders of magnitude higher than any modern computing devices. In the past few decades, there has been an acute problem of creating a quantum computer that uses quantum mechanical effects for computations. Currently, there are prototypes of devices of this class, but it is not yet possible to achieve an effective solution to the planned tasks with their help due to a number of difficulties in implementation. However, there is a mathematical apparatus that describes the behavior of quantum particles using a wave function. Hence, it becomes possible to simulate quantum computations on the classical architecture and check the reliability of algorithms belonging to the NP class, which are theoretically executed on a quantum computer in polynomial time and which cannot be solved on classical computers within an acceptable time frame. Effectively simulate the operation of a quantum system on devices with classical architecture is impossible, it remains to propose methods for acceleration of quantum computing on classical systems.

Panhellenic Conference on Informatics•Nov 26, 2021•1 citation

Quantum Neural Networks: Bridging Quantum Computing and Machine Learning

Reji Kurien Thomas

The usage of QNNs is one approach that might be used to close the knowledge gap that exists between the domains of machine learning and quantum computing. As a result of this research, a full analysis of QNNs has been offered, covering a wide range of issues including their theoretical underpinnings, training techniques, benefits, limits, applications, and assessment methodologies. Quantum neural networks, also known as QNNs, are a type of artificial neural network that makes use of the power of quantum computing. These networks provide the promise for a significant improvement in processing speed as well as greater representation capabilities. On the other hand, in order to make full advantage of the benefits that QNNs give, obstacles such as scalability concerns and hardware restrictions need to be addressed and fixed. The fact that QNNs have the potential to be applied in such a broad range of different sectors is evidence of both the adaptability and the significance of this rapidly developing field of study. It will be necessary to do more study and investigation if there is to be any hope of making headway in the field of quantum machine learning with regard to the creation of QNNs and of realizing their full potential.

Asian Journal of Research in Computer Science•Jun 15, 2023•2 citations
Over the past few decades, there has been a significant breakthrough in the field of quantum computing. Research is of growing interest, which has recently led to the development of quantum information systems prototypes and methods for their development. The paper describes the possibilities, advantages and disadvantages of quantum neural networks. The analysis of throughput, learning complexity and comparison of a classical feed-forward neural network and a quantum neural network with two different feature maps is performed.
Over the past few decades, there has been a significant breakthrough in the field of quantum computing. Research is of growing interest, which has recently led to the development of quantum information systems prototypes and methods for their development. The paper describes the possibilities, advantages and disadvantages of quantum neural networks. The analysis of throughput, learning complexity and comparison of a classical feed-forward neural network and a quantum neural network with two different feature maps is carried out.
In recent years, quantum computing has emerged as a potentially gamechanging technology, with applications across various disciplines, including AI and machine learning.In recent years, the combination of quantum computing and neural networks has led to the development of quantum neural networks (QNNs).This paper explores the potential of QNNs and their applications in solving complex problems that are challenging for classical neural networks.This paper explores the fundamental principles of quantum computing, the architecture of QNNs, and their advantages over classical neural networks.Furthermore, this will highlight key research areas and challenges in the development and utilization of QNNs.Through an in-depth analysis, it demonstrates the QNNs hold significant promise for addressing complex computational problems and advancing the field of artificial intelligence.
In recent years, classical neural networks have been widely used in various applications and have achieved remarkable success. However, with the advent of quantum computing, there is a growing interest in quantum neural networks (QNNs) as a potential alternative to classical machine learning. In this thesis, we study the architectures of quantum and classical neural networks. We also investigate the performance of QNNs compared to classical neural networks from various aspects, such as vanishing gradient, trainability, expressivity. Our experiments demonstrate that QNNs have the potential to outperform classical neural networks in specific scenarios. While more powerful QNNs exhibit improved performance compared to classical neural networks, our findings also indicate that less powerful QNNs may not always yield significant improvements. This suggests that the effectiveness of QNNs in surpassing classical approaches is contingent on factors such as network architecture, optimization techniques, problem complexity.
The last few decades have seen significant breakthroughs in the fields of deep learning and quantum computing. Research at the junction of the two fields has garnered an increasing amount of interest, which has led to the development of quantum deep learning and quantum-inspired deep learning techniques in recent times. In this work, we present an overview of advances in the intersection of quantum computing and deep learning by discussing the technical contributions, strengths and similarities of various research works in this domain. To this end, we review and summarise the different schemes proposed to model quantum neural networks (QNNs) and other variants like quantum convolutional networks (QCNNs). We also briefly describe the recent progress in quantum inspired classic deep learning algorithms and their applications to natural language processing.
Recently, there has been a rapid increase interest in quantum computers. Their work is based on the use of quantum-mechanical phenomena such as superposition and entanglement for computing to transform input data into outputs, which can actually provide effective performance 3-4 orders of magnitude higher than any modern computing devices. In the past few decades, there has been an acute problem of creating a quantum computer that uses quantum mechanical effects for computations. Currently, there are prototypes of devices of this class, but it is not yet possible to achieve an effective solution to the planned tasks with their help due to a number of difficulties in implementation. However, there is a mathematical apparatus that describes the behavior of quantum particles using a wave function. Hence, it becomes possible to simulate quantum computations on the classical architecture and check the reliability of algorithms belonging to the NP class, which are theoretically executed on a quantum computer in polynomial time and which cannot be solved on classical computers within an acceptable time frame. Effectively simulate the operation of a quantum system on devices with classical architecture is impossible, it remains to propose methods for acceleration of quantum computing on classical systems.
The usage of QNNs is one approach that might be used to close the knowledge gap that exists between the domains of machine learning and quantum computing. As a result of this research, a full analysis of QNNs has been offered, covering a wide range of issues including their theoretical underpinnings, training techniques, benefits, limits, applications, and assessment methodologies. Quantum neural networks, also known as QNNs, are a type of artificial neural network that makes use of the power of quantum computing. These networks provide the promise for a significant improvement in processing speed as well as greater representation capabilities. On the other hand, in order to make full advantage of the benefits that QNNs give, obstacles such as scalability concerns and hardware restrictions need to be addressed and fixed. The fact that QNNs have the potential to be applied in such a broad range of different sectors is evidence of both the adaptability and the significance of this rapidly developing field of study. It will be necessary to do more study and investigation if there is to be any hope of making headway in the field of quantum machine learning with regard to the creation of QNNs and of realizing their full potential.