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

Промышленные АСУ и контроллеры.

Development of Quantum Schemes for Machine Learning of Neural Networks with the Architecture of the Persecepton Based on the Principles of the Govers Algorithm

Пронин Цезарь Борисович, Andrey Vladimirovich Ostroukh

Published Dec 21, 2021• 0 citations
Publisher

Abstract

Целью данной работы, является практическое исследование возможности формирования квантовых схем для машинного обучения нейронных сетей. За основу демонстрируемых квантовых схем были взяты принципы работы квантового алгоритма Гровера (Grover’s Search Algorithm). За архитектуру примера обучаемой нейронной сети был взят персептрон. Многослойный персептрон является достаточно популярной архитектурой нейронной сети за счет масштабируемости и возможности применения для решения широкого спектра задач. The purpose of this work is a practical study of the possibility of forming quantum schemes for machine learning neural networks. The principles of operation of the Grovers Search Algorithm (Grover’s Search Algorithm) were taken as the basis of the quantum schemes. For the architecture of an example of a trained neural network was taken by Perseceptron. The multilayer perceptron is a fairly popular neural network architecture due to scalability and the possibility of applying a wide range of tasks.

DOI
10.25791/asu.12.2021.1330

Related papers

Creation and Training of Quantum Neural Networks Based on Grover’s Algorithm

Пронин Цезарь Борисович, Andrey Vladimirovich Ostroukh

В данной работе рассматривается возможность создания квантовых нейронных сетей, обучаемых с помощью алгоритма Гровера. Цель данной работы заключается в совмещении процесса обучения нейронной сети, производимого с помощью алгоритма Гровера, и функциональной структуры нейронной сети, интерпретированной в виде квантовой схемы. В качестве простого примера нейронной сети, для рассмотрения концепции, был предложен персептрон с одним обучаемым параметром – весом синапса, входящего в скрытый нейрон. This paper discusses the possibility of creating quantum neural networks trained using Grover’s algorithm. The purpose of this work is to combine the learning process of the neural network, produced using Grover’s algorithm, and the functional structure of the neural network, interpreted as a quantum circuit. As a simple example of a neural network, to consider the concept, a perceptron was proposed with one learning parameter – the weight of a synapse entering a hidden neuron.

Промышленные АСУ и контроллеры.•Nov 26, 2021•1 citation

Development of Quantum Circuits for Perceptron Neural Network Training, Based on the Principles of Grover's Algorithm

C. B. Pronin, Andrey Vladimirovich Ostroukh

This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems.

arXiv:2110.09891•Oct 15, 2021•1 citation

Creating Quantum Circuits for Training Perceptron Neural Networks on the Principles of Grover's Algorithm

C. B. Pronin, O. I. Maksimychev, Andrey Vladimirovich Ostroukh +2 more

This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems. Large scale neural networks can require significant computing resources for training purposes, therefore Grover’s quantum search algorithm could be used as a way to speed up this process, thanks to its ability of simultaneously processing multiple input values of a given function.

Systems of Signals Generating and Processing in the Field of on Board Communications•Mar 15, 2022•10 citations

Development and Training of Quantum Neural Networks, Based on the Principles of Grover's Algorithm

C. B. Pronin, Andrey Vladimirovich Ostroukh

This paper highlights the possibility of creating quantum neural networks that are trained by Grover's Search Algorithm. The purpose of this work is to propose the concept of combining the training process of a neural network, which is performed on the principles of Grover's algorithm, with the functional structure of that neural network, interpreted as a quantum circuit. As a simple example of a neural network, to showcase the concept, a perceptron with one trainable parameter - the weight of a synapse connected to a hidden neuron.

arXiv:2110.01443•Oct 1, 2021•1 citation

Модели квантового «сильного» вычислительного интеллекта и квантовых нейронных сетей глубокого обучения: платформа интеллектуального управления промышленными роботизированными социотехническими системами

Капков Р. Ю., Olga Tyatyushkina, С.В. Ульянов

The principles and methods of quantum «strong» computational intelligence model’s design based on the tools of quantum deep learning applying quantum neural networks and a quantum genetic algorithm are considered. Additional features of quantum perceptron models and quantum deep learning engineering models are discussed when using QCOptKBTM - knowledge base optimization toolkit for intelligent controllers in the tasks of quantum intelligent control of robotic sociotechnical systems in projects «Industry 4.0 / 5.0 /6.0». The description of the features of quantum deep learning allows to more accurately and deeply master the capabilities of the QCOptKBTM toolkit, which includes the stages of learning and extracting (from source data) a learning signal using the SCOptKBTM toolkit based on soft computing technology, and is further considered as classical data. Due to quantum computing operators, classical data is encoded by qubits, the optimal choice of quantum correlation between the desired solutions and the use of constructive interference is made, the desired result is extracted by measurement. Thus, the developed intelligent SCOptKBTM and QCOptKBTM tools include the principles of quantum deep learning, and, as in the case of soft computing technology, forms the optimal structure of the new quantum neural network, and through the use of a quantum genetic algorithm accelerates the search for the desired solution.

•Sep 30, 2024•0 citations

A Quantum Machine Learning Approach Using an Optimized Application of Grover's Algorithm

Mohamed Yassine Cherif, Wided Lejouad Chaari, Olfa Belkahla Driss

This paper is about studying the application of quantum computing to develop machine learning methods, in order to optimize the time of calculation for processing extensive amounts of data, thanks to the use of the quantum superposition state of information, which enables to apply parallel computation for processing different parts of data simultaneously. In fact, we introduce a quantum approach, using Grover's algorithm, to search for the optimal parameters of a perceptron classifier as a fundamental element for developing a quantum neural network, with the proposition of the training process and the comparison with the related works. The proposed approach enables yielding the optimal parameters of a perceptron classifier with one application of Grover's search method rather than applying the iterative approaches that were previously introduced in the literature.

IEEE Afro-Mediterranean Conference on Artificial Intelligence (AMCAI)•Dec 13, 2023•2 citations
Целью данной работы, является практическое исследование возможности формирования квантовых схем для машинного обучения нейронных сетей. За основу демонстрируемых квантовых схем были взяты принципы работы квантового алгоритма Гровера (Grover’s Search Algorithm). За архитектуру примера обучаемой нейронной сети был взят персептрон. Многослойный персептрон является достаточно популярной архитектурой нейронной сети за счет масштабируемости и возможности применения для решения широкого спектра задач. The purpose of this work is a practical study of the possibility of forming quantum schemes for machine learning neural networks. The principles of operation of the Grovers Search Algorithm (Grover’s Search Algorithm) were taken as the basis of the quantum schemes. For the architecture of an example of a trained neural network was taken by Perseceptron. The multilayer perceptron is a fairly popular neural network architecture due to scalability and the possibility of applying a wide range of tasks.
В данной работе рассматривается возможность создания квантовых нейронных сетей, обучаемых с помощью алгоритма Гровера. Цель данной работы заключается в совмещении процесса обучения нейронной сети, производимого с помощью алгоритма Гровера, и функциональной структуры нейронной сети, интерпретированной в виде квантовой схемы. В качестве простого примера нейронной сети, для рассмотрения концепции, был предложен персептрон с одним обучаемым параметром – весом синапса, входящего в скрытый нейрон. This paper discusses the possibility of creating quantum neural networks trained using Grover’s algorithm. The purpose of this work is to combine the learning process of the neural network, produced using Grover’s algorithm, and the functional structure of the neural network, interpreted as a quantum circuit. As a simple example of a neural network, to consider the concept, a perceptron was proposed with one learning parameter – the weight of a synapse entering a hidden neuron.
This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems. Large scale neural networks can require significant computing resources for training purposes, therefore Grover’s quantum search algorithm could be used as a way to speed up this process, thanks to its ability of simultaneously processing multiple input values of a given function.
This paper highlights the possibility of creating quantum neural networks that are trained by Grover's Search Algorithm. The purpose of this work is to propose the concept of combining the training process of a neural network, which is performed on the principles of Grover's algorithm, with the functional structure of that neural network, interpreted as a quantum circuit. As a simple example of a neural network, to showcase the concept, a perceptron with one trainable parameter - the weight of a synapse connected to a hidden neuron.
The principles and methods of quantum «strong» computational intelligence model’s design based on the tools of quantum deep learning applying quantum neural networks and a quantum genetic algorithm are considered. Additional features of quantum perceptron models and quantum deep learning engineering models are discussed when using QCOptKBTM - knowledge base optimization toolkit for intelligent controllers in the tasks of quantum intelligent control of robotic sociotechnical systems in projects «Industry 4.0 / 5.0 /6.0». The description of the features of quantum deep learning allows to more accurately and deeply master the capabilities of the QCOptKBTM toolkit, which includes the stages of learning and extracting (from source data) a learning signal using the SCOptKBTM toolkit based on soft computing technology, and is further considered as classical data. Due to quantum computing operators, classical data is encoded by qubits, the optimal choice of quantum correlation between the desired solutions and the use of constructive interference is made, the desired result is extracted by measurement. Thus, the developed intelligent SCOptKBTM and QCOptKBTM tools include the principles of quantum deep learning, and, as in the case of soft computing technology, forms the optimal structure of the new quantum neural network, and through the use of a quantum genetic algorithm accelerates the search for the desired solution.
This paper is about studying the application of quantum computing to develop machine learning methods, in order to optimize the time of calculation for processing extensive amounts of data, thanks to the use of the quantum superposition state of information, which enables to apply parallel computation for processing different parts of data simultaneously. In fact, we introduce a quantum approach, using Grover's algorithm, to search for the optimal parameters of a perceptron classifier as a fundamental element for developing a quantum neural network, with the proposition of the training process and the comparison with the related works. The proposed approach enables yielding the optimal parameters of a perceptron classifier with one application of Grover's search method rather than applying the iterative approaches that were previously introduced in the literature.