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

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

Published Sep 30, 2024• 0 citations
OpenAlex

Abstract

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.

Related papers

Квантовый алгоритм робастного интеллектуального управления процессом охлаждения азотом сверхпроводящего магнита

А. Г. Решетников, С. В. Ульянов

From the point view of quantum IT engineering, the definition of the concept and issues of intelligent control of weakly structured and poorly formalized objects with underdetermined/hidden parameters are discussed. The stages of domestic quantum IT software engineering for the design of embedded self-organizing intelligent control systems using the QSCIT (Quantum Soft Computational Intelligence Toolkit) software toolkit are presented. QSCIT is based on industrial knowledge base optimizers (SC&QC)OptKBTM and employs quantum soft computing technologies. A new type of coordinated dual-channel intelligent control of nitrogen pressure and flow valves with hidden feedback is considered in a process with a variable superconducting magnet cooling structure. In this case, the superconducting magnet is considered as a classical control object with a weakly structured, poorly formalized model with underdetermined parameters, information about which is contained in the learning signal measured on the actual object. Quantum technology for studying a highly nonlinear and dynamically unstable autonomous intelligent robot forms the basis of a system simulating the interaction of nitrogen pressure and flow valves, as well as an intelligent self-organizing quantum controller coordinating the control of nitrogen pressure and flow valves in a cryogenic superconducting magnet cooling unit in the NICA mega-science project (JINR). Quantum soft computing and quantum fuzzy inference in the quantum controller structure extract knowledge from the learning signal and, based on the extracted amount of hidden quantum information, generate additional "thermodynamic" control power as an additional information resource for the intelligent controller to perform useful work. These processes are implemented on a classical processor. The generation of this additional information resource is possible due to the existence (experimentally proven in the study) of a quantum synergistic effect of self-organization of imprecise knowledge bases: from a finite number of imprecise knowledge bases, quantum fuzzy inference generates a robust knowledge base in real time. An entropy analysis of the controllers' operation demonstrated the rational use of useful resources by the quantum intelligent controller, necessary to guarantee the achievement of the control goal. The efficiency and quantum advantage of using intelligent self-organizing quantum controllers (embedded in onboard intelligent control systems) to control classical control objects based on quantum soft computing technologies are demonstrated.

System Analysis in Science and Education•Jun 5, 2026•0 citations

ИТ моделирования самоорганизующихся интеллектуальных контроллеров на основе квантового глубокого машинного обучения

Sergey Victorovich Ulyanov, Andrey G. Reshetnikov, Зрелова Д. П.

The physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model. The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed and described. An approach is considered for constructing reference control models based on new laws of quantum deep machine learning applying Lagrange/Hamilton neural networks. This work develops the approach of self-organized intelligent control, describing the strategy of designing intelligent cognitive control systems based on quantum and soft computing. The synergetic effect of the quantum self-organization of the knowledge base, extracted from the non-robust knowledge bases of the intelligent fuzzy controller, is demonstrated. The information-thermodynamic law of quantum self-organization of the optimal distribution of the basic qualities of control (stability, controllability and robustness) and the law of quantum information thermodynamics on the possibility of extracting additional useful work based on the extracted quantum information hidden in classical states are applied. Formed (without violating the second law of quantum thermodynamics) on the basis of the extracted amount of hidden quantum information, the "thermodynamic" control force allows the robot (as an object of control) to perform quantitatively more useful work compared to the amount of work spent (on extracting quantum hidden information). The guaranteed achievement of the goal of controlling the robot is carried out on the basis of a designed intelligent cognitive control system using the quantum knowledge base optimizer – QCOptKBTM, the structure of which includes a quantum fuzzy inference – QFI. The quantum algorithm of self-organization of non-robust QFI knowledge bases is structurally based on the synergetic effects of hidden quantum information to implement the optimal distribution of management qualities. This technology makes it possible to increase the reliability of intelligent cognitive control systems in control situations under uncertainty. The examples demonstrated the effectiveness of introducing the QFI scheme as a ready-made programmable algorithmic solution for embedded intelligent control systems. Обсуждается физическая интерпретация процесса управления самоорганизацией на квантовом уровне на основе квантовых информационно-термодинамических моделей обмена и извлечения квантовой (скрытой) ценностной информации из/между классическими траекториями частиц в модели «рой взаимодействующих частиц». Представлены и описываются основные физические и информационно-термодинамические аспекты модели квантового интеллектуального управления классическими объектами управления. Рассматривается подход построения эталонных моделей управления на основе новых законов квантового глубокого машинного обучения с применением квантовых нейронных сетей Лагранжа/Гамильтона. Данная работа развивает подход самоорганизующегося интеллектуального управления, описывая стратегию проектирования интеллектуальных систем когнитивного управления на основе квантовых и мягких вычислений. Продемонстрирован синергетический эффект квантовой самоорганизации базы знаний, извлеченный из не робастных баз знаний интеллектуального нечеткого регулятора. Применяется информационно-термодинамический закон квантовой самоорганизации оптимального распределения базисных качеств управления (устойчивость, управляемость и робастность) и закон квантовой информационной термодинамики о возможности извлечения дополнительной полезной работы на основе извлеченной квантовой информации, скрытой в классических состояниях. Сформированная (без нарушения второго закона квантовой термодинамики) на основе извлеченного количества скрытой квантовой информации «термодинамическая» сила управления позволяет роботу (как объекту управления) совершить количественно большую полезную работу по сравнению с количеством затраченной (на извлечение квантовой скрытой информации) работу. Гарантированное достижение цели управления роботом осуществляется на основе спроектированной интеллектуальной когнитивной системы управления с применением инструментария квантового оптимизатора баз знаний QCOptKBTM, в структуру которого включен квантовый нечеткий вывод – КНВ. Квантовый алгоритм самоорганизации не робастных баз знаний КНВ структурно опирается на синергетические эффекты от скрытой квантовой информации для осуществления реализации оптимального распределения качеств управления. Данная технология позволяет повысить надежность интеллектуальных когнитивных систем управления в ситуациях управления в условиях неопределенности. Примеры продемонстрировали эффективность введения схемы КНВ в качестве готового программируемого алгоритмического решения для встраиваемых интеллектуальных систем управления.

Sovremennye informacionnye tehnologii i IT-obrazovanie.•Jun 30, 2023•0 citations

Квантовый генетический алгоритм в задачах моделирования интеллектуального управления и суперкомпьютинг

С.В. Ульянов, Sergey Victorovich Ulyanov, Рябов Н. В. +1 more

This paper considers the use of the quantum genetic algorithm for automatic selection of the optimum type and kind of correlation in the quantum structure of fuzzy inference.When solving intelligent and cognitive control tasks based on quantum soft computing and the principles of quantum deep machine learning, it is important to choose the type and kind of quantum correlation.It is an additional physical and informational computing resource in the formation of the laws of the time variation of the gains of traditional regulators located at the lower (performing) level of the intelligent control system structure.This approach is essential for the realization of adaptive and self-organizing processes of knowledge bases and guaranteed to achieve the control objectives under contingency control situations.Successful solution of the problem of choosing the type and kind of quantum correlations allows strengthening the successful search for solutions of algorithmically unsolvable problems at the classical control level.A genetic algorithm is a powerful computational intelligence toolkit for random searching of effective solutions for poorly formalized tasks.However, it has a big disadvantage when used on a classic computer: low speed and dependence on the expert's choice of a decision-making space.The paper describes the types of quantum genetic algorithms based on a combination of quantum and classical calculations, and an algorithm consisting only of quantum calculations.In such algorithm, a population can be composed of only one chromosome in a state of superposition.Immersion in the quantum structure of the fuzzy inference quantum genetic algorithm provides a synergistic effect and allows realizing quantum fuzzy inference on a classical processor.The new effect is based on the quantum genetic algorithm extracting information hidden in the classical state laws change over time the gains of traditional regulators on a new unexpected situation control.Such synergistic effect is possible only with end-to-end intellectual information technology of quantum computing and is absent at the classical level of application of the classical computing technology.

Международный журнал Программные продукты и системы•Jun 3, 2019•3 citations

Self-organized intelligent quantum controller: quantum deep learning and quantum genetic algorithm – QSCOptKBTM toolkit

Зрелова Д. П., V. Korenkov, Andrey Reshetnikov +2 more

Strategy of intelligent cognitive control systems of ill-defined control objects based on quantum and soft computing presented. Quantum self-organization knowledge base synergetic effect extracted from intelligent fuzzy controller’s imperfect knowledge bases described. That technology improved of robustness of intelligent cognitive control systems in hazard control situations described with different types of robot cooperation. Examples demonstrated the introduction of quantum fuzzy inference gate design as prepared programmable algorithmic solution for board embedded control systems. The physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model. The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed and described. An approach is considered for constructing reference control models based on new laws of quantum deep machine learning applying neural networks in mega-science project NICA.

International Workshop on Deep Learning in Computational Physics (DLCP)•Nov 17, 2022•2 citations

Quantum Fast Algorithm Computational Intelligence PT I: SW / HW Smart Toolkit

Sergey Victorovich Ulyanov

A new approach to a circuit implementation design of quantum algorithm gates for quantum massive parallel fast computing implementation is presented. The main attention is focused on the development of design method of fast quantum algorithm operators as superposition, entanglement and interference which are in general time-consuming operations due to the number of products that have to be performed. SW & HW support sophisticated smart toolkit of supercomputing accelerator of quantum algorithm simulation is described. The method for performing Grover’s interference without product operations as Benchmark introduced. The background of developed information technology is the "Quantum / Soft Computing Optimizer" (QSCOptKBTM) software based on soft and quantum computational intelligence toolkit. Quantum genetic and quantum fuzzy inference algorithm gate design considered. The quantum information technology of imperfect knowledge base self-organization design of fuzzy robust controllers for the guaranteed achievement of intelligent autonomous robot the control goal in unpredicted control situations is described.

Artificial Intelligence Advances•Jul 19, 2019•18 citations

Промышленная роботизированная интеллектуальная робастная система управления: применение технологий квантовых мягких вычислений и квантовой программной инженерии в неопределенных условиях управления

Сергей Викторович Ульянов, S.V. Ulyanov, А.Г. Решетников +3 more

The strategy for designing intelligent control systems based on quantum and soft computing technologies is described.The synergetic effect of quantum self-organization of a robust knowledge base, extracted from imperfect knowledge bases of an intelligent fuzzy controller, is presented.The developed technology improves the reliability of intelligent cognitive control systems in unforeseen control situations, for example, with various types of interacting robots.Benchmarks demonstrated the effective implementation of a quantum fuzzy inference circuit as a readymade programmable algorithmic solution for lower-level control systems embedded in a standard board, demonstrated the quantum superiority of quantum intelligent control of classical control objects, expanding the Feynman-Manin thesis.The correct physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model.A new information synergetic effect is demonstrated: a robust knowledge base of a quantum fuzzy controller is created in real time from two unreliable knowledge bases of a fuzzy controller.This effect is purely quantum in nature and uses hidden quantum information extracted from classical states.The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed.

Международный журнал Программные продукты и системы•Mar 3, 2023•1 citation
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.
From the point view of quantum IT engineering, the definition of the concept and issues of intelligent control of weakly structured and poorly formalized objects with underdetermined/hidden parameters are discussed. The stages of domestic quantum IT software engineering for the design of embedded self-organizing intelligent control systems using the QSCIT (Quantum Soft Computational Intelligence Toolkit) software toolkit are presented. QSCIT is based on industrial knowledge base optimizers (SC&QC)OptKBTM and employs quantum soft computing technologies. A new type of coordinated dual-channel intelligent control of nitrogen pressure and flow valves with hidden feedback is considered in a process with a variable superconducting magnet cooling structure. In this case, the superconducting magnet is considered as a classical control object with a weakly structured, poorly formalized model with underdetermined parameters, information about which is contained in the learning signal measured on the actual object. Quantum technology for studying a highly nonlinear and dynamically unstable autonomous intelligent robot forms the basis of a system simulating the interaction of nitrogen pressure and flow valves, as well as an intelligent self-organizing quantum controller coordinating the control of nitrogen pressure and flow valves in a cryogenic superconducting magnet cooling unit in the NICA mega-science project (JINR). Quantum soft computing and quantum fuzzy inference in the quantum controller structure extract knowledge from the learning signal and, based on the extracted amount of hidden quantum information, generate additional "thermodynamic" control power as an additional information resource for the intelligent controller to perform useful work. These processes are implemented on a classical processor. The generation of this additional information resource is possible due to the existence (experimentally proven in the study) of a quantum synergistic effect of self-organization of imprecise knowledge bases: from a finite number of imprecise knowledge bases, quantum fuzzy inference generates a robust knowledge base in real time. An entropy analysis of the controllers' operation demonstrated the rational use of useful resources by the quantum intelligent controller, necessary to guarantee the achievement of the control goal. The efficiency and quantum advantage of using intelligent self-organizing quantum controllers (embedded in onboard intelligent control systems) to control classical control objects based on quantum soft computing technologies are demonstrated.
The physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model. The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed and described. An approach is considered for constructing reference control models based on new laws of quantum deep machine learning applying Lagrange/Hamilton neural networks. This work develops the approach of self-organized intelligent control, describing the strategy of designing intelligent cognitive control systems based on quantum and soft computing. The synergetic effect of the quantum self-organization of the knowledge base, extracted from the non-robust knowledge bases of the intelligent fuzzy controller, is demonstrated. The information-thermodynamic law of quantum self-organization of the optimal distribution of the basic qualities of control (stability, controllability and robustness) and the law of quantum information thermodynamics on the possibility of extracting additional useful work based on the extracted quantum information hidden in classical states are applied. Formed (without violating the second law of quantum thermodynamics) on the basis of the extracted amount of hidden quantum information, the "thermodynamic" control force allows the robot (as an object of control) to perform quantitatively more useful work compared to the amount of work spent (on extracting quantum hidden information). The guaranteed achievement of the goal of controlling the robot is carried out on the basis of a designed intelligent cognitive control system using the quantum knowledge base optimizer – QCOptKBTM, the structure of which includes a quantum fuzzy inference – QFI. The quantum algorithm of self-organization of non-robust QFI knowledge bases is structurally based on the synergetic effects of hidden quantum information to implement the optimal distribution of management qualities. This technology makes it possible to increase the reliability of intelligent cognitive control systems in control situations under uncertainty. The examples demonstrated the effectiveness of introducing the QFI scheme as a ready-made programmable algorithmic solution for embedded intelligent control systems. Обсуждается физическая интерпретация процесса управления самоорганизацией на квантовом уровне на основе квантовых информационно-термодинамических моделей обмена и извлечения квантовой (скрытой) ценностной информации из/между классическими траекториями частиц в модели «рой взаимодействующих частиц». Представлены и описываются основные физические и информационно-термодинамические аспекты модели квантового интеллектуального управления классическими объектами управления. Рассматривается подход построения эталонных моделей управления на основе новых законов квантового глубокого машинного обучения с применением квантовых нейронных сетей Лагранжа/Гамильтона. Данная работа развивает подход самоорганизующегося интеллектуального управления, описывая стратегию проектирования интеллектуальных систем когнитивного управления на основе квантовых и мягких вычислений. Продемонстрирован синергетический эффект квантовой самоорганизации базы знаний, извлеченный из не робастных баз знаний интеллектуального нечеткого регулятора. Применяется информационно-термодинамический закон квантовой самоорганизации оптимального распределения базисных качеств управления (устойчивость, управляемость и робастность) и закон квантовой информационной термодинамики о возможности извлечения дополнительной полезной работы на основе извлеченной квантовой информации, скрытой в классических состояниях. Сформированная (без нарушения второго закона квантовой термодинамики) на основе извлеченного количества скрытой квантовой информации «термодинамическая» сила управления позволяет роботу (как объекту управления) совершить количественно большую полезную работу по сравнению с количеством затраченной (на извлечение квантовой скрытой информации) работу. Гарантированное достижение цели управления роботом осуществляется на основе спроектированной интеллектуальной когнитивной системы управления с применением инструментария квантового оптимизатора баз знаний QCOptKBTM, в структуру которого включен квантовый нечеткий вывод – КНВ. Квантовый алгоритм самоорганизации не робастных баз знаний КНВ структурно опирается на синергетические эффекты от скрытой квантовой информации для осуществления реализации оптимального распределения качеств управления. Данная технология позволяет повысить надежность интеллектуальных когнитивных систем управления в ситуациях управления в условиях неопределенности. Примеры продемонстрировали эффективность введения схемы КНВ в качестве готового программируемого алгоритмического решения для встраиваемых интеллектуальных систем управления.
This paper considers the use of the quantum genetic algorithm for automatic selection of the optimum type and kind of correlation in the quantum structure of fuzzy inference.When solving intelligent and cognitive control tasks based on quantum soft computing and the principles of quantum deep machine learning, it is important to choose the type and kind of quantum correlation.It is an additional physical and informational computing resource in the formation of the laws of the time variation of the gains of traditional regulators located at the lower (performing) level of the intelligent control system structure.This approach is essential for the realization of adaptive and self-organizing processes of knowledge bases and guaranteed to achieve the control objectives under contingency control situations.Successful solution of the problem of choosing the type and kind of quantum correlations allows strengthening the successful search for solutions of algorithmically unsolvable problems at the classical control level.A genetic algorithm is a powerful computational intelligence toolkit for random searching of effective solutions for poorly formalized tasks.However, it has a big disadvantage when used on a classic computer: low speed and dependence on the expert's choice of a decision-making space.The paper describes the types of quantum genetic algorithms based on a combination of quantum and classical calculations, and an algorithm consisting only of quantum calculations.In such algorithm, a population can be composed of only one chromosome in a state of superposition.Immersion in the quantum structure of the fuzzy inference quantum genetic algorithm provides a synergistic effect and allows realizing quantum fuzzy inference on a classical processor.The new effect is based on the quantum genetic algorithm extracting information hidden in the classical state laws change over time the gains of traditional regulators on a new unexpected situation control.Such synergistic effect is possible only with end-to-end intellectual information technology of quantum computing and is absent at the classical level of application of the classical computing technology.
Strategy of intelligent cognitive control systems of ill-defined control objects based on quantum and soft computing presented. Quantum self-organization knowledge base synergetic effect extracted from intelligent fuzzy controller’s imperfect knowledge bases described. That technology improved of robustness of intelligent cognitive control systems in hazard control situations described with different types of robot cooperation. Examples demonstrated the introduction of quantum fuzzy inference gate design as prepared programmable algorithmic solution for board embedded control systems. The physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model. The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed and described. An approach is considered for constructing reference control models based on new laws of quantum deep machine learning applying neural networks in mega-science project NICA.
A new approach to a circuit implementation design of quantum algorithm gates for quantum massive parallel fast computing implementation is presented. The main attention is focused on the development of design method of fast quantum algorithm operators as superposition, entanglement and interference which are in general time-consuming operations due to the number of products that have to be performed. SW & HW support sophisticated smart toolkit of supercomputing accelerator of quantum algorithm simulation is described. The method for performing Grover’s interference without product operations as Benchmark introduced. The background of developed information technology is the "Quantum / Soft Computing Optimizer" (QSCOptKBTM) software based on soft and quantum computational intelligence toolkit. Quantum genetic and quantum fuzzy inference algorithm gate design considered. The quantum information technology of imperfect knowledge base self-organization design of fuzzy robust controllers for the guaranteed achievement of intelligent autonomous robot the control goal in unpredicted control situations is described.
The strategy for designing intelligent control systems based on quantum and soft computing technologies is described.The synergetic effect of quantum self-organization of a robust knowledge base, extracted from imperfect knowledge bases of an intelligent fuzzy controller, is presented.The developed technology improves the reliability of intelligent cognitive control systems in unforeseen control situations, for example, with various types of interacting robots.Benchmarks demonstrated the effective implementation of a quantum fuzzy inference circuit as a readymade programmable algorithmic solution for lower-level control systems embedded in a standard board, demonstrated the quantum superiority of quantum intelligent control of classical control objects, expanding the Feynman-Manin thesis.The correct physical interpretation of the process of controlling self-organization at the quantum level is discussed on the basis of quantum information-thermodynamic models of exchange and extraction of quantum (hidden) valuable information from/between classical particle trajectories in the "swarm of interacting particles" model.A new information synergetic effect is demonstrated: a robust knowledge base of a quantum fuzzy controller is created in real time from two unreliable knowledge bases of a fuzzy controller.This effect is purely quantum in nature and uses hidden quantum information extracted from classical states.The main physical and information-thermodynamic aspects of the model of quantum intelligent control of classical control objects are discussed.