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

International Conference on Signal Processing

A learning algorithm for quantum neuron

Li Fei, Xiaoliang Dong, Shengmei Zhao, Baoyu Zheng

Published Jun 28, 2005• 4 citations
Publisher

Abstract

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.

DOI
10.1109/icosp.2004.1441621

Related papers

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

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 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

Nonlinear quantum neuron: A fundamental building block for quantum neural networks

Shilu Yan, Hongsheng Qi, Wei Cui

Quantum computing enables quantum neural networks (QNNs) to have great potential to surpass artificial neural networks. The powerful generalization of neural networks is attributed to nonlinear activation functions. Although various models related to QNNs have been developed, they are facing the challenge of merging the nonlinear, dissipative dynamics of neural computing into the linear, unitary quantum system. In this paper, we establish different quantum circuits to approximate nonlinear functions and then propose a generalizable framework to realize any nonlinear quantum neuron. We present two quantum neuron examples based on the proposed framework. The quantum resources required to construct a single quantum neuron are polynomial in function of the input size. Finally, both IBM Quantum Experience results and numerical simulations illustrate the effectiveness of the proposed framework.

arXiv:2011.03429•Physical Review A•Nov 25, 2020•46 citations

Quantum Neuron: an elementary building block for machine learning on quantum computers

Yudong Cao, Gian Giacomo Guerreschi, Alán Aspuru‐Guzik

Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.

arXiv:1711.11240•Nov 30, 2017•113 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
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.
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.
Quantum computing enables quantum neural networks (QNNs) to have great potential to surpass artificial neural networks. The powerful generalization of neural networks is attributed to nonlinear activation functions. Although various models related to QNNs have been developed, they are facing the challenge of merging the nonlinear, dissipative dynamics of neural computing into the linear, unitary quantum system. In this paper, we establish different quantum circuits to approximate nonlinear functions and then propose a generalizable framework to realize any nonlinear quantum neuron. We present two quantum neuron examples based on the proposed framework. The quantum resources required to construct a single quantum neuron are polynomial in function of the input size. Finally, both IBM Quantum Experience results and numerical simulations illustrate the effectiveness of the proposed framework.
Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.
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.