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

Applied Sciences

Quantum Classification Algorithm Based on Competitive Learning Neural Network and Entanglement Measure

Mohammed Zidan, Abdel‐Haleem Abdel‐Aty, Mahmoud El-shafei, Marwa Feraig, Yazeed A. Al-Sbou, Hichem Eleuch, Mahmoud Abdel‐Aty

Published Mar 27, 2019• 79 citations
Publisher

Abstract

In this paper, we develop a novel classification algorithm that is based on the integration between competitive learning and the computational power of quantum computing. The proposed algorithm classifies an input into one of two binary classes even if the input pattern is incomplete. We use the entanglement measure after applying unitary operators to conduct the competition between neurons in order to find the winning class based on wining-take-all. The novelty of the proposed algorithm is shown in its application to the quantum computer. Our idea is validated via classifying the state of Reactor Coolant Pump of a Risky Nuclear Power Plant and compared with other quantum-based competitive neural networks model.

DOI
10.3390/app9071277

Related papers

A quantum classification algorithm for classification incomplete patterns based on entanglement measure

Abdel‐Haleem Abdel‐Aty, Heba Kadry, Mohammed Zidan +3 more

In this paper, a novel quantum classification algorithm that is based on competitive learning is presented to classify an input pattern that results from the failures of some sensors. As long as an incomplete pattern is presented to our model, the proposed algorithm performs the competitions between the neurons by applying some unitary transformations then measures the degree of entanglement using concurrence measure to find the winner class based on the winner-take-all technique. The proposed algorithm finds the most likely winning class label in between two binary competitive classes for an incomplete pattern presented to the proposed model. Because larger scale quantum computers are still in the lab, we studied the proposed algorithm on a case study.

Journal of Intelligent & Fuzzy Systems•Dec 31, 2019•51 citations

An autonomous competitive learning algorithm using quantum hamming neural networks

Mohammed Zidan, Alaa Sagheer, NASSER METWALLY

Quantum neural network is a fledging research domain based on the merge of classical neural network and quantum computing. In this paper, we add the quantum effect to the classical hamming neural network algorithm in order to employ the advantages of quantum information to yield, finally, a novel quantum competitive learning algorithm. The proposed algorithm, called quantum hamming neural network (QHNN), is capable to recognize incomplete patterns, as well as, increase the probability of recognizing patterns on the account of undesired patterns. Moreover, these undesired patterns could be used as new patterns for training the algorithm in subsequent steps. The proposed algorithm is testified via a case study and a classification experiment, where promising results, reaches to 100%, are given and compared favorably with other reported quantum competitive algorithms.

International Joint Conference on Neural Networks (IJCNN)•Jul 1, 2015•16 citations

Self-Organizing Quantum Neural Network

Ri‐Gui Zhou, Hongyuan Zheng, Nan Jiang +1 more

This paper combines quantum computation with conventional artificial neural network theory to present a novel network - self-organizing quantum neural network (SOQNN) that can perform pattern classification self-organizationally and automatically through quantum competitive process. It does not need to prestore some given patterns but can classify input patterns with higher classification rapidity than that of classical neural networks(CNN).Further, SOQNN make the analogical pattern win easily in the next quantum competitive process by modifying the value of the quantum register(QR) corresponding to the pattern classified.

International Joint Conference on Neural Networks (IJCNN)•Jan 1, 2006•8 citations

Quantum Competition Network Model Based On Quantum Entanglement

Yanhua Zhong, Chang-qing Yuan

This paper proposes a quantum competition neural network model compared to its classical counterpart from the relative parts of the complex system localizing operation without changing the perspective of entanglement measure. It shows that the pseudo-state is an inevitable part of the quantum competitive model. After the initialization of the quantum neural network; quantum competitive network is capable of associative memory through local area of operations because of the existence of these pseudo-states. Furthermore, Competitive algorithms of quantum theory are given, and finally an example of pattern recognition for simulation. Simulation results show that a quantum competitive learning algorithm in the learning rate and convergence rate is far better than the basic competitive artificial neural network.

Journal of Computers•Sep 1, 2012•9 citations

Application of Quantum Self-Organization Mapping Networks to Classification

Yang Jing

A quantum self-organization mapping networks model based on quantum neurons is presented in this paper. Both the input and the weight of the model are represented by the quantum bits, and the output of the model is represented by the real number. The model is composed of input layer and competitive layer. First, the samples are transformed into quantum states and are submitted to the input layer, and then the similar coefficients of quantum states are computed between the inputs and the weights. Secondly, the implicit pattern characters of the clustering samples are extracted in the competitive layer, and then the clustering results are showed. The quantum states of weights are updated by quantum rotation gates. The networks are trained by the algorithm combining the unsupervised learning and supervised learning together. Finally two experiments demonstrate that the model and algorithm are evidently superior to the general self-organization mapping networks.

Applied Mechanics and Materials•Sep 1, 2013•4 citations

Machine classification of quantum correlations for entanglement distribution networks

Jan Soubusta, Antonín Černoch, Karel Lemr

The paper suggest employing machine learning for resource-efficient classification of quantum correlations in entanglement distribution networks. Specifically, artificial neural networks (ANN) are utilized to classify quantum correlations based on collective measurements conducted in the geometry of entanglement swapping. ANNs are trained to categorize two-qubit quantum states into five mutually exclusive classes depending on the strength of quantum correlations exhibited by the states. The precision and recall of the ANN models are analyzed as functions of the quantum resources consumed, i.e. the number of collective measurements performed.

arXiv:2402.09212•Feb 14, 2024•0 citations
In this paper, we develop a novel classification algorithm that is based on the integration between competitive learning and the computational power of quantum computing. The proposed algorithm classifies an input into one of two binary classes even if the input pattern is incomplete. We use the entanglement measure after applying unitary operators to conduct the competition between neurons in order to find the winning class based on wining-take-all. The novelty of the proposed algorithm is shown in its application to the quantum computer. Our idea is validated via classifying the state of Reactor Coolant Pump of a Risky Nuclear Power Plant and compared with other quantum-based competitive neural networks model.
In this paper, a novel quantum classification algorithm that is based on competitive learning is presented to classify an input pattern that results from the failures of some sensors. As long as an incomplete pattern is presented to our model, the proposed algorithm performs the competitions between the neurons by applying some unitary transformations then measures the degree of entanglement using concurrence measure to find the winner class based on the winner-take-all technique. The proposed algorithm finds the most likely winning class label in between two binary competitive classes for an incomplete pattern presented to the proposed model. Because larger scale quantum computers are still in the lab, we studied the proposed algorithm on a case study.
Quantum neural network is a fledging research domain based on the merge of classical neural network and quantum computing. In this paper, we add the quantum effect to the classical hamming neural network algorithm in order to employ the advantages of quantum information to yield, finally, a novel quantum competitive learning algorithm. The proposed algorithm, called quantum hamming neural network (QHNN), is capable to recognize incomplete patterns, as well as, increase the probability of recognizing patterns on the account of undesired patterns. Moreover, these undesired patterns could be used as new patterns for training the algorithm in subsequent steps. The proposed algorithm is testified via a case study and a classification experiment, where promising results, reaches to 100%, are given and compared favorably with other reported quantum competitive algorithms.
This paper combines quantum computation with conventional artificial neural network theory to present a novel network - self-organizing quantum neural network (SOQNN) that can perform pattern classification self-organizationally and automatically through quantum competitive process. It does not need to prestore some given patterns but can classify input patterns with higher classification rapidity than that of classical neural networks(CNN).Further, SOQNN make the analogical pattern win easily in the next quantum competitive process by modifying the value of the quantum register(QR) corresponding to the pattern classified.
This paper proposes a quantum competition neural network model compared to its classical counterpart from the relative parts of the complex system localizing operation without changing the perspective of entanglement measure. It shows that the pseudo-state is an inevitable part of the quantum competitive model. After the initialization of the quantum neural network; quantum competitive network is capable of associative memory through local area of operations because of the existence of these pseudo-states. Furthermore, Competitive algorithms of quantum theory are given, and finally an example of pattern recognition for simulation. Simulation results show that a quantum competitive learning algorithm in the learning rate and convergence rate is far better than the basic competitive artificial neural network.
A quantum self-organization mapping networks model based on quantum neurons is presented in this paper. Both the input and the weight of the model are represented by the quantum bits, and the output of the model is represented by the real number. The model is composed of input layer and competitive layer. First, the samples are transformed into quantum states and are submitted to the input layer, and then the similar coefficients of quantum states are computed between the inputs and the weights. Secondly, the implicit pattern characters of the clustering samples are extracted in the competitive layer, and then the clustering results are showed. The quantum states of weights are updated by quantum rotation gates. The networks are trained by the algorithm combining the unsupervised learning and supervised learning together. Finally two experiments demonstrate that the model and algorithm are evidently superior to the general self-organization mapping networks.
The paper suggest employing machine learning for resource-efficient classification of quantum correlations in entanglement distribution networks. Specifically, artificial neural networks (ANN) are utilized to classify quantum correlations based on collective measurements conducted in the geometry of entanglement swapping. ANNs are trained to categorize two-qubit quantum states into five mutually exclusive classes depending on the strength of quantum correlations exhibited by the states. The precision and recall of the ANN models are analyzed as functions of the quantum resources consumed, i.e. the number of collective measurements performed.