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 Mathematics & Information Sciences

Analysis of quantum neural network learning ability

Yanhua Zhong, Chang-qing Yuan

Published May 14, 2013• 5 citations
Publisher

Abstract

Quantum Hamiltonian of the system of analysis of quantum neuron. A theoretical quantum neural network model is proposed by quantum neural model of wave functions. Quantum Turing machine operator in a single step has been constructed and the study algorithm has been presented. Simulation results show that quantum neuron has a strong ability to learn. Finally some other related problems about quantum neural computation have been discussed.

DOI
10.12785/amis/072l43

Related papers

On the Features of Quantum Neuron

Li Fei

Quantum Neural Networks (QNN) is naturally the next step in the evolution of neuro-computing system. QNN may give us unprecedented possibilities in creating new system for information processing. The fundamentals of QNN are introduced, a model for quantum neuron is described. A quantum learning algorithm is proposed and its convergence property is discussed. The computational power of the quantum neuron is explored. Numerical and graphical results show that this single quantum neuron can perform XOR function unrealizable with a classical neuron and has the same computational power as the two-layer NN, it can be used to realize nonlinear mapping.

Journal of Circuits and Systems•Jan 1, 2004•2 citations

A learning algorithm for quantum neuron

Li Fei, Xiaoliang Dong, Shengmei Zhao +1 more

Most proposals for quantum neural networks (QNN) have skipped over the problem of how to learn the networks. This paper describes a novel model for quantum neuron and proposes its learning algorithm. It can be shown that this algorithm works on quantum systems and the convergence result demonstrates efficient performance of the proposed quantum neuron. Numerical and graphical results show that this single quantum neuron can perform the XOR function unrealizable with a classical neuron and can eliminate the necessity of building a network of neurons to obtain nonlinear mapping.

International Conference on Signal Processing•Jun 28, 2005•4 citations

A study of quantum neural networks

Li Fei, Zheng Baoyu

The study of quantum neural networks (QNN) may give us unprecedented possibilities in creating new systems for information processing. We describe a model for quantum neuron (QN) and discuss the quantum learning rule. It is demonstrated that this single quantum neuron is able to perform the XOR function unrealizable with a single classical neuron and has the same computational power as the two-layer perceptron.

International Conference on Neural Networks and Signal Processing•Jan 1, 2003•16 citations

Learning Algorithm and Application of Quantum Neural Networks with Quantum Weights

Dianbao Mu, Zunyou Guan, Hong Zhang

A novel neural networks model with quantum weights is present.Firstly, based on the information processing modes of biology neuron and quantum computing theory, a quantum neuron model is presented, which is composed of weighting, aggregating, activating, and inspiriting.Secondly the quantum neural networks model based on quantum neuron is constructed in which the input and the output are real vectors; the linked weight and the activation value are qubits.On the basic of the gradient descent algorithm, a learning algorithm of this model is proposed.It is shown that this algorithm is super-linearly convergent under certain conditions and can increase the probability of getting the global optimal solution.Finally, the availability of the model is illustrated in both convergence speed and convergence rate by two application examples of pattern recognition and function approximation.

International Journal of Computer Theory and Engineering•Jan 1, 2013•27 citations

A STUDY OF QUANTUM NEURAL NETWORKS

Telecommunications Nanjing

The study of Quantum Neural Networks (QNN) may give us unprecedented possibilities in creating new systems for information processing. We describe a model for Quantum Neuron(QN) and discuss the quantum learning rule. It is demonstrated that this single quantum neuron is able to perform the XOR function unrealizable with a single classical neuron and has the same computational power as the two-layer perceptron.

•Jan 1, 2003•0 citations

Hybrid Quantum Neural Networks Model Algorithm and Simulation

Hong Yu Xiao, Maojun Cao

A quantum neural networks model based on quantum neurons and traditional neurons is presented in this paper. The input of quantum neuron is real vector, its weight is quantum bits, its transforming function is an inner product operator and its output is a real number. The network includes three layers. Input layer is composed of traditional neurons that receive input information. Hidden layer is composed of quantum neurons that extract pattern feature of input information and transfer them to output layer. Output layer is composed of traditional neurons that export calculation result. The weightings of output layer are rectified by back propagation algorithm. The weightings of hidden layer are rectified by a group of quantum gates. A detailed learning algorithm is designed. Finally the availability of the model and algorithm is illustrated by two application examples of pattern recognition and functional approximation.

International Conference on Natural Computation (ICNC)•Jan 1, 2009•11 citations
Quantum Hamiltonian of the system of analysis of quantum neuron. A theoretical quantum neural network model is proposed by quantum neural model of wave functions. Quantum Turing machine operator in a single step has been constructed and the study algorithm has been presented. Simulation results show that quantum neuron has a strong ability to learn. Finally some other related problems about quantum neural computation have been discussed.
Quantum Neural Networks (QNN) is naturally the next step in the evolution of neuro-computing system. QNN may give us unprecedented possibilities in creating new system for information processing. The fundamentals of QNN are introduced, a model for quantum neuron is described. A quantum learning algorithm is proposed and its convergence property is discussed. The computational power of the quantum neuron is explored. Numerical and graphical results show that this single quantum neuron can perform XOR function unrealizable with a classical neuron and has the same computational power as the two-layer NN, it can be used to realize nonlinear mapping.
Most proposals for quantum neural networks (QNN) have skipped over the problem of how to learn the networks. This paper describes a novel model for quantum neuron and proposes its learning algorithm. It can be shown that this algorithm works on quantum systems and the convergence result demonstrates efficient performance of the proposed quantum neuron. Numerical and graphical results show that this single quantum neuron can perform the XOR function unrealizable with a classical neuron and can eliminate the necessity of building a network of neurons to obtain nonlinear mapping.
A novel neural networks model with quantum weights is present.Firstly, based on the information processing modes of biology neuron and quantum computing theory, a quantum neuron model is presented, which is composed of weighting, aggregating, activating, and inspiriting.Secondly the quantum neural networks model based on quantum neuron is constructed in which the input and the output are real vectors; the linked weight and the activation value are qubits.On the basic of the gradient descent algorithm, a learning algorithm of this model is proposed.It is shown that this algorithm is super-linearly convergent under certain conditions and can increase the probability of getting the global optimal solution.Finally, the availability of the model is illustrated in both convergence speed and convergence rate by two application examples of pattern recognition and function approximation.
A quantum neural networks model based on quantum neurons and traditional neurons is presented in this paper. The input of quantum neuron is real vector, its weight is quantum bits, its transforming function is an inner product operator and its output is a real number. The network includes three layers. Input layer is composed of traditional neurons that receive input information. Hidden layer is composed of quantum neurons that extract pattern feature of input information and transfer them to output layer. Output layer is composed of traditional neurons that export calculation result. The weightings of output layer are rectified by back propagation algorithm. The weightings of hidden layer are rectified by a group of quantum gates. A detailed learning algorithm is designed. Finally the availability of the model and algorithm is illustrated by two application examples of pattern recognition and functional approximation.